# Exoskeleton (Wearable Robotics)

> Source: https://aiwiki.ai/wiki/exoskeleton
> Updated: 2026-06-23
> Categories: Healthcare AI, Robotics
> From AI Wiki (https://aiwiki.ai), a free encyclopedia of artificial intelligence. Quote with attribution.

| Exoskeleton | |
| --- | --- |
| **Type** | [Wearable robotics](/wiki/wearable_robotics) |
| **Also known as** | Powered exoskeleton, exosuit, wearable robot, bionic suit |
| **Primary domains** | Medical rehabilitation, industrial ergonomics, military load assistance, recreation |
| **Earliest powered prototype** | GE Hardiman (1965) |
| **First FDA-cleared personal device** | ReWalk (2014) |
| **First FDA-cleared self-balancing system** | [Wandercraft](/wiki/wandercraft) Atalante X (2024) |
| **Common sensors** | Surface electromyography (sEMG), inertial measurement units (IMUs), foot-pressure insoles, force/torque cells, joint encoders |
| **Common AI methods** | [Deep learning](/wiki/deep_learning), [reinforcement learning](/wiki/reinforcement_learning), recurrent and convolutional networks, sim-to-real transfer |
| **Key research labs** | UC Berkeley Robotics and Human Engineering Lab, Harvard Biodesign Lab, Stanford Biomechatronics, University of Tsukuba Cybernics Lab |
| **Estimated 2025 market size** | USD 2.1 to 3.4 billion (varies by analyst) |

An **exoskeleton**, sometimes called a **powered exoskeleton**, **exosuit**, or **wearable robot**, is a powered or passive mechanical structure worn on the body to augment, assist, or restore human movement. Modern exoskeletons combine actuated joints, lightweight structural members, biological sensors and increasingly sophisticated [artificial intelligence](/wiki/artificial_intelligence) controllers that interpret a wearer's intent and modulate assistance in real time. The field sits at the intersection of [robotics](/wiki/robotics), biomechanics, neural engineering, and [wearable robotics](/wiki/wearable_robotics), and it has produced devices that allow paralyzed patients to walk, factory workers to lift heavy loads with reduced injury risk, and soldiers to carry larger payloads over longer distances.

The single most-cited proof that exoskeletons can help healthy people in everyday conditions came in October 2022, when a Stanford team led by Steve Collins published a controller, optimized during one hour of walking in a public setting, that increased a wearer's self-selected walking speed by 9 plus or minus 4% and reduced the energy used to travel a given distance by 17 plus or minus 5% compared with normal shoes.[30] On a treadmill the same assistance cut metabolic energy consumption by 23 plus or minus 8%, and the authors note that their outdoor, data-driven method identified the best assistance settings roughly four times faster than laboratory protocols.[30][31] This shift from laboratory to real world, and from hand-tuned control to machine-learned control, is the defining story of the modern exoskeleton.

The modern exoskeleton industry is roughly 60 years old in concept and about 15 years old as a practical commercial reality. After a half-century of research-grade prototypes, lower-limb medical exoskeletons received their first U.S. Food and Drug Administration (FDA) clearances between 2014 and 2016, with [ReWalk Robotics](https://www.rewalk.com), [Ekso Bionics](/wiki/ekso), [Indego](https://www.indego.com), and [Cyberdyne](/wiki/cyberdyne) HAL all receiving regulatory clearance for clinical or personal use during that window.[1][2] The industrial segment commercialized in parallel, with passive lifting vests from Comau, German Bionic, Ottobock, Hyundai and several other manufacturers reaching factory floors at Ford, BMW, Toyota, Stellantis, Boeing and Airbus by the late 2010s.[3] Military programs, beginning with General Electric's Hardiman in 1965 and continuing through DARPA's BLEEX program, the Lockheed Martin Human Universal Load Carrier (HULC) and the canceled Tactical Assault Light Operator Suit (TALOS), have repeatedly demonstrated the difficulty of building powered armor that does not exhaust the wearer faster than it helps them.[4]

The most consequential change in the past five years has been the maturation of AI-driven control. Older exoskeletons relied on hand-tuned finite-state controllers that switched between preset assistance profiles for walking, sitting and stair climbing. Current research systems use [deep learning](/wiki/deep_learning) for gait phase detection from inertial and electromyographic signals, [reinforcement learning](/wiki/reinforcement_learning) policies trained in simulated musculoskeletal environments, and increasingly transformer-based foundation models that generalize across users and activities without per-subject tuning.[5][6] In June 2024 a Nature paper from Stanford's biomechatronics group demonstrated a hip exoskeleton trained entirely in simulation that reduced metabolic cost by 24.3% during walking, 13.1% during running and 15.4% during stair climbing on its first deployment, with no per-subject calibration; the result is widely cited as a milestone for sim-to-real transfer in wearable robotics, although follow-up work in 2026 has reexamined some of the reported energy figures.[6][7]

## What is an exoskeleton?

The term *exoskeleton*, borrowed from biology, originally referred to the rigid external skeletons of arthropods and crustaceans. In engineering it now refers to any wearable mechanical system that runs in parallel with the wearer's musculoskeletal system, with the intent of either augmenting human strength or endurance, restoring mobility lost to injury or disease, or reducing musculoskeletal strain during repetitive labor. Devices range from rigid, full-body powered armor to soft, fabric-based "exosuits" that look more like athletic apparel than machinery.

Three characteristics distinguish a wearable robotic exoskeleton from a more conventional orthosis or brace:

1. The device contains one or more **actuators** (electric motors, hydraulic cylinders, pneumatic chambers, or passive springs) that store, release, or generate mechanical work to influence the wearer's movement.
2. The device contains **sensors** that read either the wearer's biological signals (EMG, EEG), kinematic state (IMU, joint encoders), or interaction forces (load cells, foot-pressure insoles).
3. The device contains a **controller** that closes the loop between sensors and actuators, ideally in real time and ideally without disrupting the wearer's natural intent.

Passive exoskeletons, such as the Comau MATE-XT and most industrial back-support vests, contain no electric power source. Instead they use carefully tuned springs or elastic elements to redistribute load. Active or powered exoskeletons add motors, batteries, and a software controller, which raises capability but also raises weight, cost, and the risk that the device fights the wearer rather than helping.

## What are the main types of exoskeletons?

| Category | Primary Goal | Typical Users | Representative Products |
| --- | --- | --- | --- |
| Medical and rehabilitation | Restore or retrain gait after spinal cord injury, stroke, multiple sclerosis, brain injury, cerebral palsy | Inpatient and outpatient rehab patients, personal users with paraplegia | ReWalk, Ekso GT, EksoNR, Indego, Cyberdyne HAL, Wandercraft Atalante X |
| Industrial and occupational | Reduce musculoskeletal strain during lifting, overhead work, kneeling and prolonged standing | Automotive assembly, warehouse, construction, shipbuilding, agriculture | Comau MATE-XT, German Bionic Cray X, Hyundai H-WEX and CEX, Levitate Airframe, Ottobock Paexo |
| Military and load-bearing | Carry heavy loads over long distances without fatiguing the wearer | Infantry, special operations, logistics personnel | GE Hardiman (research), DARPA BLEEX, Lockheed Martin HULC, Lockheed ONYX, Sarcos Guardian XO |
| Augmentation and recreation | Increase performance or endurance for able-bodied users in sport or daily life | Skiers, hikers, mobility-limited consumers | Roam Robotics Elevate, Roam Ascend, Arc'teryx MO/GO (with Skip Innovations), Hypershell |
| Pediatric and home-care | Restore mobility in children with neuromuscular disease or rehabilitate at home | Pediatric patients with cerebral palsy, spinal muscular atrophy | Trexo Robotics Plus, MyoSwiss MyoSuit, ABLE Human Motion |

A single device may straddle two categories. The Cyberdyne HAL platform, for example, exists in both a clinical version (HAL for Medical Use) and an industrial-labor version (HAL for Care Support and HAL Lumbar Type for caregivers).[8]

## History

### Origins (1890 to 1965)

The earliest patented design for a body-worn assistance device dates to the 1890 Russian inventor Nicholas Yagn, who proposed a passive bag of compressed-gas springs to assist walking, running and jumping. Yagn's apparatus was never built and would not have functioned as drawn. Several other speculative patents appeared in the early 20th century, but no powered prototype was constructed until General Electric's Hardiman in the 1960s.

### Hardiman (1965)

General Electric's *Hardiman* was the first serious attempt to build a powered exoskeleton. Funded by the U.S. Office of Naval Research and the U.S. Army, it was developed at GE's Schenectady research center between 1965 and 1971. Hardiman was a hydraulic and electric full-body suit intended to multiply the wearer's strength by a factor of 25, allowing a 110 kilogram lift to feel like 4.5 kilograms.[4] In practice the suit weighed roughly 680 kilograms, moved at about 0.76 meters per second, and was so unstable that engineers could only safely operate one arm at a time. When both legs were powered, GE's own engineers described the resulting motion as "violent and uncontrollable," and the project was shelved without a single human ever wearing the full suit.[4] Hardiman established that powered exoskeletons would require dramatic advances in sensors, actuators, batteries and control theory before they could ever leave the laboratory.

### BLEEX and the DARPA Era (2000 to 2008)

In 2000 the U.S. Defense Advanced Research Projects Agency (DARPA) launched the Exoskeletons for Human Performance Augmentation (EHPA) program, which funded a new generation of academic and corporate research. The most influential output was the Berkeley Lower Extremity Exoskeleton (BLEEX), built at the University of California, Berkeley by Homayoon Kazerooni's Robotics and Human Engineering Lab. Unveiled in 2004, BLEEX had seven degrees of freedom per leg, a hydraulic actuation system, and an internal-combustion engine that made it the first untethered, energy-autonomous lower-limb exoskeleton. It could carry a 75 kilogram payload at 0.9 meters per second.[9] BLEEX directly seeded several commercial efforts: Berkeley Bionics (later renamed Ekso Bionics) was founded in 2005, and Lockheed Martin licensed a derivative platform that became HULC.

### HAL and the Birth of Cyberdyne (2004 to 2018)

In parallel with BLEEX, the Japanese roboticist Yoshiyuki Sankai at the University of Tsukuba had been developing the Hybrid Assistive Limb (HAL) since the late 1990s. Sankai began mapping motor neurons in human legs in 1990, designed early prototypes between 1997 and 2003, and founded [Cyberdyne](/wiki/cyberdyne) in June 2004 to commercialize HAL. HAL is distinguished by a unique control approach. Skin-mounted electrodes detect bioelectric signals leaking through the skin a few hundred milliseconds before the underlying muscles contract, and the suit provides matching mechanical assistance during the same movement, creating a tight closed loop between intent and motion that Sankai calls *cybernic voluntary control*.[10] In Cyberdyne's own description, this Cybernic Voluntary Control "provides physical support based on the wearer's intention" read from bioelectric muscle signals, while a complementary Cybernic Autonomous Control handles motions for which no clear voluntary signal is available.[10][8]

HAL received CE marking in Europe in 2013 and U.S. FDA 510(k) clearance in late 2017, with commercial U.S. deployment beginning at Brooks Rehabilitation in Jacksonville, Florida in March 2018. Cleared indications include rehabilitation for spinal cord injury, stroke, and certain progressive neuromuscular diseases.[10][11]

### The First Wave of Medical Exoskeletons (2010 to 2018)

Between 2010 and 2018 a cohort of medical exoskeletons reached the market, mostly aimed at rehabilitation centers and a smaller number aimed at personal use by people with spinal cord injuries.

- **eLEGS / Ekso / Ekso GT / EksoNR ([Ekso Bionics](/wiki/ekso))**: Berkeley Bionics introduced its rehabilitation suit as eLEGS in 2010, renamed Ekso in 2011, and launched the FDA-cleared Ekso GT in 2016 with stroke rehabilitation as a labeled use. EksoNR followed in 2020 and remains the only exoskeleton with FDA clearance for both stroke and acquired brain injury.[12]
- **ReWalk ([ReWalk Robotics](https://www.rewalk.com))**: Founded by Israeli entrepreneur Amit Goffer in 2001, ReWalk became the first powered exoskeleton cleared by the FDA for personal at-home use, in June 2014.[13] The device was popularized by trial user Claire Lomas, who completed the 2012 London Marathon in a ReWalk over the course of 17 days.
- **Indego (Parker Hannifin, later Ekso)**: Spun out from Vanderbilt University and commercialized by Parker Hannifin, Indego received FDA 510(k) clearance for clinical use in March 2016 and personal use later that year. Parker Hannifin sold the Indego business to Ekso Bionics in 2023, consolidating two of the major U.S. medical exoskeleton brands.[14]

A notable structural feature of these devices was their reliance on crutches or other balance aids: none of them was self-balancing, which meant the wearer still had to manage trunk balance manually.

### Self-Balancing and AI-Native Exoskeletons (2019 to present)

The French startup [Wandercraft](https://www.wandercraft.eu), founded in Paris in 2012, developed *Atalante*, the first self-balancing lower-limb exoskeleton that allows hands-free walking by patients with paralysis. Atalante uses model-based dynamic balance control inspired by the same bipedal-locomotion theory that drives a modern [humanoid robot](/wiki/humanoid_robot), eliminating the need for crutches.[15] Atalante X received its initial FDA clearance in early 2024 for spinal cord injury at levels T5 to L5, was cleared for hemiplegia from cerebrovascular accidents soon after, and in November 2025 the FDA expanded the cleared population to spinal cord injury from C4 to L5 and to multiple sclerosis.[16] In June 2025 Wandercraft closed a $75 million Series D round to fund global commercialization of Atalante and the rollout of *Eve*, a personal at-home version of the self-balancing exoskeleton planned for U.S. launch in 2026.[17] During the 2024 Paris Olympics torch relay, Wandercraft's personal exoskeleton allowed Kevin Piette, a wheelchair user, to walk a leg of the torch route, the first time a self-balancing exoskeleton had been used in such a public ceremonial setting.[15]

## Notable Products and Manufacturers

### Medical Exoskeletons

| Product | Manufacturer | First Cleared | Indication | Distinguishing Feature |
| --- | --- | --- | --- | --- |
| ReWalk Personal | [ReWalk Robotics](https://www.rewalk.com) | FDA 2014 | Spinal cord injury, T7 to L5 | First FDA personal-use clearance for a powered exoskeleton |
| Ekso GT | [Ekso Bionics](/wiki/ekso) | FDA 2016 | Stroke and spinal cord injury | First clinical exoskeleton cleared for stroke rehabilitation |
| EksoNR | [Ekso Bionics](/wiki/ekso) | FDA 2020 | Stroke, SCI, acquired brain injury, multiple sclerosis | Only device cleared for brain injury and MS |
| Indego Therapy and Personal | Parker Hannifin (later Ekso) | FDA 2016 (clinical and personal) | Spinal cord injury, T3 to L5 | Modular design weighs 12 kg, lightest in class at launch |
| HAL Lower Limb Type | [Cyberdyne](/wiki/cyberdyne) | FDA 2017 | SCI, stroke, neuromuscular disease | Bioelectric (sEMG) intent control |
| Atalante X | Wandercraft | FDA 2024, expanded 2025 | SCI C4 to L5, MS, hemiplegia | First FDA-cleared self-balancing exoskeleton |
| Trexo Plus | Trexo Robotics | Pediatric | Cerebral palsy, SMA | Pediatric gait training in clinic and home |
| MyoSuit | MyoSwiss (Switzerland) | CE | Generalized lower-limb weakness | Soft, lightweight, portable |

### Industrial Exoskeletons

| Product | Manufacturer | Type | Body Region | Notable Adopters |
| --- | --- | --- | --- | --- |
| Cray X | German Bionic | Active, powered | Lower back / lift assist | Logistics, automotive |
| Apogee and Apogee+ | German Bionic | Active, powered | Lower back / lift assist, plus posture coaching AI | Logistics, healthcare |
| MATE-XT and MATE-XT GO | Comau | Passive | Shoulders / overhead work | Stellantis, Iveco, Maserati |
| H-WEX (Waist EXoskeleton) | [Hyundai](/wiki/hyundai) | Passive | Lower back | Hyundai factories worldwide |
| H-VEX (Vest EXoskeleton) | [Hyundai](/wiki/hyundai) | Passive | Shoulders, overhead work | Hyundai assembly plants |
| CEX (Chairless EXoskeleton) | [Hyundai](/wiki/hyundai) | Passive | Legs and lower back, sit-stand | Hyundai standing-work stations |
| EksoVest and EVO | [Ekso Bionics](/wiki/ekso) | Passive | Shoulders, overhead work | Ford, Toyota, Boeing |
| Levitate Airframe | Levitate Technologies | Passive | Shoulders, overhead work | BMW, Boeing, dental clinics |
| Paexo Shoulder, Back, Thumb | Ottobock | Passive | Shoulders, back, thumb | VW, Audi |
| Phoenix and ShieldX | SuitX (acquired by Ottobock 2021) | Passive and active variants | Lower limb, back, shoulders | Construction, automotive |
| Guardian XO | Sarcos / Palladyne AI | Active, full body | Whole body | Material handling pilots, Delta Air Lines, Sumitomo |

### Military and Augmentation

| Product | Developer | Status | Notes |
| --- | --- | --- | --- |
| Hardiman | General Electric | Canceled 1971 | First powered exoskeleton attempt; never operationally worn |
| BLEEX | UC Berkeley / DARPA | Research only | First untethered lower-limb exoskeleton (2004) |
| HULC (Human Universal Load Carrier) | Berkeley Bionics, licensed to Lockheed Martin | Discontinued | Carried 90 kg loads but increased metabolic cost in U.S. Army trials |
| ONYX | Lockheed Martin | Field tested | Lower-limb actuated knee assist; under 6 kg powered weight |
| TALOS (Tactical Assault Light Operator Suit) | U.S. Special Operations Command | Concluded 2019 | $80 million program; produced spinoff technologies but no fielded suit |
| Soft Exosuit | Harvard Biodesign Lab and DARPA Warrior Web | Research and licensing | Conor Walsh's textile-based hip and ankle exosuits |
| Elevate Ski Exoskeleton | Roam Robotics | Commercial | Pneumatic recreational exoskeleton for skiing |
| Ascend | Roam Robotics | Commercial | Knee assist for osteoarthritis and weak quadriceps |
| MO/GO | Skip Innovations and Arc'teryx | Commercial | Outdoor hiking exoskeleton pant launched in 2024 |

## How does an exoskeleton sense and control movement?

A modern exoskeleton's sensing stack typically includes some combination of the following.

- **Inertial Measurement Units (IMUs)** mounted at the trunk, thigh, shank and foot provide three-axis accelerations and angular rates, used for kinematic reconstruction and gait phase detection.
- **Foot-pressure insoles** provide ground reaction force estimates without an external force plate, useful for detecting heel strike, mid-stance and toe-off events.
- **Surface electromyography (sEMG)** electrodes detect electrical activity in skeletal muscles 100 to 200 milliseconds before the muscle contracts mechanically, providing an early signal of motion intent.
- **Joint encoders and motor torque sensors** provide direct measurement of the suit's own kinematic and force state.
- **Force / torque cells** at the human-suit interface measure interaction forces and are used to detect resistance, slipping, or unintended fighting between user and device.

The controller layer has evolved through three broad generations.

1. **Finite-state machines (1990s to early 2010s).** Early controllers explicitly enumerated gait phases (heel strike, mid-stance, push-off, swing) and switched between hand-tuned PID assistance profiles based on threshold rules over IMU and pressure data. These controllers worked but generalized poorly across users, terrain and walking speeds.
2. **Model-based dynamic control (2010s to present).** Higher-end systems including Atalante used model-predictive control over reduced-order biomechanical models to maintain dynamic balance, borrowing heavily from humanoid robotics research.[15]
3. **Learning-based control (2018 to present).** Recent research replaces hand-tuned controllers with neural networks trained either supervisedly on motion-capture data or by [reinforcement learning](/wiki/reinforcement_learning) in simulation.[5][6]

## How is AI and machine learning used in exoskeleton control?

| AI Approach | Function | Representative Result |
| --- | --- | --- |
| Convolutional neural networks (CNNs) on sEMG plus IMU | Motion classification, gait phase recognition | 99.3% classification accuracy across walking, running, stair climbing in ankle exoskeleton studies[5] |
| Bidirectional LSTM on sEMG | Online gait-phase estimation 120 ms ahead of mechanical motion | Robust stance and swing detection for hip and knee exoskeletons[18] |
| Deep CNN on IMU plus plantar pressure | Five-phase gait cycle recognition | Used in commercial soft ankle exoskeletons for cerebral palsy[19] |
| Human-in-the-loop optimization (real world) | Online tuning of assistance to minimize energy cost during natural walking | 17% lower energy per distance and 9% faster self-selected speed after one hour of outdoor optimization[30] |
| Model-free [reinforcement learning](/wiki/reinforcement_learning) (TD3, PPO) | End-to-end controller for walking, sit-to-stand, squat assistance | Squat assistance and crutch-force minimization for lower-limb exoskeletons[20] |
| Sim-to-real [deep learning](/wiki/deep_learning) on musculoskeletal models | Versatile policy that generalizes across activities and users | Hip exoskeleton reduces metabolic cost by 24.3% (walking), 13.1% (running), 15.4% (stair climbing) on first deployment[6] |
| Recurrent musculoskeletal coupling | Robust torque control under uncertain interaction forces | Stable walking control under variable patient-suit force coupling[20] |
| Foundation-model-style transformer policies | Multimodal sensor fusion across morphologies | Active research direction inspired by RT-1, RT-2, and Octo for general manipulation robotics |

### Intent Prediction

Intent prediction is the task of inferring what a wearer is about to do, ideally before they begin to do it, so that the suit can match assistance to motion rather than fight it. EMG signals lead the corresponding mechanical contraction by about 100 to 200 milliseconds, which is enough lead time to drive a motor and complete a coordinated assist. Convolutional and recurrent neural networks have been applied to this problem with steadily improving accuracy. A 2025 study published in Scientific Reports used three IMUs and eight textile-electrode sEMG sensors with a CNN to classify ankle exoskeleton motions with 99.263% accuracy, surpassing prior gel-electrode studies and improving long-term wearability.[5]

### Gait Phase Detection

Deep learning has largely replaced threshold-based finite-state machines for gait phase detection. A 2024 study published in MDPI Sensors used a bidirectional LSTM on multi-muscle sEMG data during exoskeleton-assisted walking and identified stance and swing phases with high accuracy 120 ms in advance of the kinematic transition, exploiting the natural electromechanical delay of skeletal muscle to enable predictive rather than reactive control.[18]

### Human-in-the-Loop Optimization in the Real World

Before controllers could be trained entirely offline, the dominant way to personalize an exoskeleton was *human-in-the-loop optimization*: the device repeatedly varies its assistance parameters while sensors estimate the wearer's energy cost, and an optimizer searches for the setting that minimizes effort for that specific person. Early demonstrations from Steve Collins's group and collaborators ran this loop on a treadmill with a respirometry mask, which limited it to the laboratory. The breakthrough came in October 2022, when Patrick Slade, Mykel Kochenderfer, Scott Delp and Collins published *Personalizing exoskeleton assistance while walking in the real world* in Nature, replacing the metabolic mask with a data-driven estimate from inexpensive wearable sensors so that optimization could run outdoors.[30] The authors report that "assistance optimized during one hour of naturalistic walking in a public setting increased self-selected speed by 9 plus or minus 4% and reduced the energy used to travel a given distance by 17 plus or minus 5% compared with normal shoes," and that the same assistance cut metabolic energy by 23 plus or minus 8% on a treadmill at 1.5 meters per second.[30] Stanford described it as the first time an untethered exoskeleton delivered energy savings to users outside the lab, with the outdoor method converging on optimal settings about four times faster than treadmill-based protocols.[31]

### Reinforcement Learning Controllers

Several groups have demonstrated that model-free [reinforcement learning](/wiki/reinforcement_learning) can produce robust exoskeleton controllers without requiring hand-engineered gait models. Algorithms such as Twin Delayed Deep Deterministic Policy Gradient (TD3) and Proximal Policy Optimization (PPO) are commonly used. A 2023 paper in the Journal of NeuroEngineering and Rehabilitation reported a deep RL controller for a lower-limb rehabilitation exoskeleton trained on a coupled musculoskeletal model and three independent neural networks; the controller delivered reliable walking assistance under uncertain interaction forces between user and suit.[20] A separate 2024 arXiv paper used RL to minimize crutch loading forces in a lower-limb medical exoskeleton, an explicit safety objective rarely captured by classical controllers.[21]

### Sim-to-Real Transfer and Foundation Models

The 2024 Nature paper from Steve Collins's group at Stanford, with Shuzhen Luo as lead author, demonstrated that reinforcement learning over a high-fidelity musculoskeletal simulator could produce a single hip-exoskeleton controller that performed across walking, running and stair climbing without per-subject calibration, reducing measured metabolic cost on first deployment.[6] The authors state that the learned controller "automatically generates assistance across different activities," reducing metabolic rates "by 24.3%, 13.1% and 15.4% for walking, running and stair climbing, respectively," framing simulation-based learning as "a generalizable and scalable strategy" for assistive robots.[6] The result was widely cited as the first convincing demonstration of sim-to-real transfer for a wearable robot. A 2026 follow-up bioRxiv preprint reexamined the published metabolic results, arguing that some reported energy savings exceed physiological limits relating mechanical power to metabolic cost during gait, which has triggered an ongoing methodological discussion.[7]

At the time of writing in early 2026, several research groups are adapting transformer-based foundation-model architectures from general robotics, including ideas from Google DeepMind's RT-1 and RT-2 and the Open X-Embodiment Octo policy, to exoskeleton control. The motivation is the same as in manipulation robotics: a single policy pretrained across many users, sensors and devices may generalize better than per-device controllers that have to be tuned for each new wearer.

## Industrial Deployments

### Automotive

Automotive assembly lines have been the largest single industrial buyer of exoskeletons, primarily because so many assembly tasks involve repetitive overhead work, sustained awkward postures, or heavy lifting. Major automotive deployments include the following.

- **Ford Motor Company** rolled out the Levitate Airframe and the EksoVest across 15 U.S. plants beginning in 2017, the largest industrial exoskeleton deployment of its era.
- **BMW** uses Levitate Airframe vests at multiple plants and has tested several other systems through its industrial-engineering group.
- **Toyota** has trialed Ekso EVO at multiple North American plants for overhead assembly work.
- **Stellantis** (formed from the FCA-PSA merger) deploys Comau MATE-XT exoskeletons at multiple Maserati and Iveco plants in Italy.
- **[Hyundai](/wiki/hyundai) Motor Group** developed its own family of exoskeletons in-house. The H-WEX, revealed at CES 2017, supports the lower back during waist-flexion tasks. The CEX, first shown in 2018, is a chairless exoskeleton that lets workers maintain a sitting posture without a chair, weighing only 1.6 kg yet supporting up to 150 kg with a reported 40% reduction in lower-body muscle activity. The H-VEX, unveiled in 2019, is a vest-style exoskeleton for overhead automotive assembly that weighs 2.5 kg, 22 to 42% less than competing products, and provides up to 5.5 kgf of upward force across six adjustable assistance levels.[3][22]

### Aerospace and Logistics

Boeing has used the EksoVest at the Everett, Washington plant for overhead 787 assembly work. Airbus has tested the Skelex 360-XFR, a passive shoulder support, at its Hamburg plant. Logistics operators including DHL, GXO Logistics and Iron Mountain have deployed German Bionic Cray X and Apogee active back-support systems for repetitive lifting in distribution centers.[23] Delta Air Lines and Sumitomo conducted pilot deployments of the Sarcos Guardian XO full-body exoskeleton for heavy material handling, although Sarcos paused commercialization of the Guardian XO in 2022 in favor of focusing on AI software for robotics under the renamed Palladyne AI brand.[24]

### Construction and Trades

Construction adoption has been slower than automotive due to the unstructured nature of jobsites, but passive shoulder and back-support exoskeletons from SuitX, Ottobock and HeroWear are increasingly used by drywallers, electricians and heating ventilation and air-conditioning installers for sustained overhead work and material handling.

## Military Programs

Military exoskeleton programs have repeatedly run into the metabolic-cost problem: a powered suit must add less metabolic burden than the load it is helping carry, otherwise the soldier is more tired wearing the suit than without it. The Lockheed Martin HULC, derived from BLEEX, was tested by the U.S. Army Natick Soldier Research, Development and Engineering Center in the early 2010s and showed *increased* metabolic cost compared to soldiers carrying equivalent loads with conventional rucksacks, leading to the project's termination.[4] The U.S. Special Operations Command's TALOS program, launched in 2013 by Admiral William McRaven and intended to produce a powered armored suit for special operators, was wound down in 2019 after spending roughly $80 million; it produced useful spinoffs in helmets, optics and ballistic materials but no operational exoskeleton.[4]

The Lockheed Martin ONYX, a partial lower-limb exoskeleton with knee actuators, AI-driven assistance modulation and a published unloaded weight under 6 kilograms, was tested with the U.S. Army's 10th Mountain Division and won a Popular Science Best of What's New award in 2018.[25] The U.S. Army Soldier Center has subsequently funded smaller, more modest exoskeleton programs aimed at specific tasks (logistics handling, evacuation litter carrying) rather than full powered armor for combat infantry.

A notable trend in military research is convergence with the commercial industrial market: rather than building bespoke combat suits, programs increasingly procure modified versions of devices originally designed for warehouse, construction or rehabilitation use.

## Soft Exosuits

A distinct branch of wearable robotics, the *soft exosuit*, was pioneered by Conor Walsh's lab at the Harvard Biodesign Lab in collaboration with the Wyss Institute and supported in part by the DARPA Warrior Web program. Rather than rigid frames, soft exosuits use textile webbing, Bowden cables and small motors at the waist or backpack to deliver assistive forces through the wearer's own skeleton.[26] Walsh's team has shown that soft hip exosuits can reduce the metabolic cost of walking and running, and a 2024 collaboration with Boston University demonstrated that a soft hip exosuit eliminated freezing-of-gait episodes for a participant with Parkinson's disease during indoor walking, a result published in Nature Medicine.[26][27] The technology has been licensed to multiple commercial spinouts, including Verve Motion (industrial back support) and Imago Rehab (stroke rehabilitation).

## Acquisitions, Mergers and Industry Consolidation

The exoskeleton industry has seen significant consolidation as it transitions from research curiosity to commercial product.

- **Ottobock acquires SuitX (2021).** The German prosthetics giant Ottobock acquired SuitX, the UC Berkeley spinout founded by Homayoon Kazerooni, in November 2021, combining SuitX's industrial and medical exoskeletons with Ottobock's existing Paexo line.[28]
- **Ekso Bionics acquires Indego (2023).** Ekso Bionics acquired Parker Hannifin's Indego business in early 2023, consolidating two of the major U.S. medical exoskeleton portfolios under a single brand.[14]
- **Sarcos becomes Palladyne AI (2024).** Sarcos Technology and Robotics, which went public via a SPAC merger in 2021 with about $496 million in capital, paused commercialization of its Guardian XO full-body exoskeleton in 2022 and rebranded itself as Palladyne AI in 2024 to focus on robotics control software, including software for third-party exoskeletons.[24]
- **Wandercraft Series D (2025).** Wandercraft closed a $75 million Series D round in June 2025 alongside a separate 25 million euro European Investment Bank loan; the company also expanded into industrial humanoid robotics through a partnership with Renault Group.[15][17]

## How big is the exoskeleton market?

Market size estimates vary widely. As of 2025, analysts including Fortune Business Insights, MarketsAndMarkets, Grand View Research and Mordor Intelligence published global market values between roughly USD 0.6 billion and USD 3.4 billion, with consensus around USD 2 to 3 billion. Forecast compound annual growth rates over the 2025 to 2030 horizon range from roughly 19% to over 40%, reflecting both the early stage of the industry and uncertainty about which application segments will scale fastest. Most analysts expect medical and industrial applications to dominate near-term revenue, with augmentation, recreation and military as longer-term growth opportunities.[29]

| Analyst | 2025 Market Size | Forecast End Year | Forecast Value | CAGR |
| --- | --- | --- | --- | --- |
| MarketsAndMarkets | USD 0.56 billion | 2030 | USD 2.03 billion | 19.2% |
| Fortune Business Insights | USD 3.52 billion (2026) | 2034 | USD 64.2 billion | 43.7% |
| Mordor Intelligence | USD 3.37 billion | 2030 | USD 13.5 billion | 32.1% |
| Straits Research | USD 3.44 billion | 2033 | USD 30.8 billion | 31.5% |
| FactMR | USD 2.1 billion | 2035 | USD 13.4 billion | 23.6% |

North America held the largest share in 2025, driven by FDA-cleared medical adoption and large-scale industrial pilots, while Asia Pacific (especially Japan, South Korea and China) is forecast to grow fastest.[29]

## What challenges still limit exoskeletons?

Despite progress, several challenges still constrain widespread deployment.

- **Battery life and weight.** A practical full-day powered exoskeleton must operate for 8 to 10 hours on a single charge while remaining light enough that the suit itself does not become a load. This is still difficult for full lower-limb systems and effectively impossible for full-body powered suits.
- **Donning and doffing time.** Many medical exoskeletons require 10 to 30 minutes to put on with assistance, which limits use in busy clinical or home settings.
- **Cost and reimbursement.** Personal medical exoskeletons cost USD 70,000 to 150,000, and reimbursement coverage from insurers including Medicare and the U.S. Department of Veterans Affairs has expanded but remains uneven.
- **Generalization.** AI controllers trained on a small set of users often fail when deployed on someone with a different gait or anthropometry; the search for sim-to-real and cross-user generalization is an active research frontier.
- **Safety.** Powered exoskeletons can fall and can injure the wearer if a control loop fails. Robust fault detection, controlled failure modes and self-balancing recovery are still active areas of work.
- **Regulatory pathway.** The FDA's medical exoskeleton review pathway, originally established for ReWalk via a de novo Class II authorization in 2014, has been refined with each subsequent device, but newly capable systems including self-balancing suits, AI-driven control and at-home use create novel regulatory questions about safety, post-market surveillance and software updates.

## Outlook

The exoskeleton field is at an inflection point comparable to where surgical robotics was in the early 2000s or where autonomous driving was in the mid-2010s. Hardware has matured to the point where reliable, FDA-cleared powered suits are commercially available; AI-driven control is rapidly closing the gap between research demonstrations and clinical or industrial usability; and a small but growing number of consumer-facing recreational and home-care products is opening the category to non-clinical buyers. Whether the industry will follow the path of surgical robotics, where one player (Intuitive Surgical) eventually captured most of the market, or the path of consumer wearables, where many specialized brands serve overlapping niches, is an open question that will likely be answered over the second half of the 2020s.

## See Also

- [Robotics](/wiki/robotics)
- [Wearable robotics](/wiki/wearable_robotics)
- [Humanoid robot](/wiki/humanoid_robot)
- [Reinforcement learning](/wiki/reinforcement_learning)
- [Deep learning](/wiki/deep_learning)
- [Cyberdyne](/wiki/cyberdyne)
- [Ekso](/wiki/ekso)
- [Hyundai](/wiki/hyundai)
- [Artificial intelligence](/wiki/artificial_intelligence)

## References

1. U.S. Food and Drug Administration, ReWalk de novo classification, K131798, 2014
2. U.S. Food and Drug Administration, Indego 510(k) clearance K152416, March 2016 and personal-use clearance later in 2016
3. Hyundai Motor Group, "VEX (Vest EXoskeleton), making smart factories a reality," Hyundai Robotics blog and just-auto.com coverage, 2019
4. Wikipedia, "Human Universal Load Carrier"; IEEE Spectrum, "The Rise of the Body Bots"; Wearethemighty.com, "The military is closing in on powerful exoskeleton technology"
5. Scientific Reports, "Deep learning for motion classification in ankle exoskeletons using surface EMG and IMU signals," 2025, https://www.nature.com/articles/s41598-025-22103-1
6. Nature, Luo et al., "Experiment-free exoskeleton assistance via learning in simulation," June 2024, https://www.nature.com/articles/s41586-024-07382-4
7. bioRxiv preprint, "Experiment-free learning of exoskeleton assistance remains an unsolved problem," 2026, https://www.biorxiv.org/content/10.64898/2026.04.01.715109v1
8. Cyberdyne, "HAL Lower Limb Type and HAL Lumbar Type product information," Cyberdyne Inc., Tsukuba, Japan
9. Berkeley Robotics and Human Engineering Laboratory, "On the Mechanical Design of the Berkeley Lower Extremity Exoskeleton (BLEEX)," 2005, https://www.jychen.cn/download/2005_BLEEX_mechanical_design.pdf
10. Medical Device Network, "HAL: The Japanese cyborg medical exoskeleton helping US patients walk again"
11. Brooks Rehabilitation, "Revolutionary Robotic Treatment For Patients With Spinal Cord Injuries Now Available In United States," March 2018
12. Ekso Bionics, "EksoNR product information," https://eksobionics.com/
13. ReWalk Robotics, FDA de novo authorization documentation, 2014
14. Exoskeleton Report, "Ekso Indego" product page, https://exoskeletonreport.com/product/indego/
15. Wandercraft, "Atalante X: A new kind of rehabilitation," https://en.wandercraft.eu/atalante-x-rehabilitation-exoskeleton; The Robot Report, "Wandercraft starts clinical trial for Personal Exoskeleton"
16. The Robot Report, "Wandercraft earns second FDA clearance for Atalante X exoskeleton," November 2025; MassDevice, "FDA expands indications for Wandercraft robotic exoskeleton"
17. The Robot Report, "Wandercraft raises $75M to scale exoskeletons, humanoids," June 2025; European Investment Bank, "Medical robotics company Wandercraft receives EUR 25 million in EIB financing," 2024
18. MDPI Sensors, "A Recurrent Deep Network for Gait Phase Identification from EMG Signals During Exoskeleton-Assisted Walking," 2024, https://www.mdpi.com/1424-8220/24/20/6666
19. Frontiers in Bioengineering and Biotechnology, "Gait phase recognition of children with cerebral palsy via deep learning based on IMU data from a soft ankle exoskeleton," 2025
20. Journal of NeuroEngineering and Rehabilitation, "Robust walking control of a lower limb rehabilitation exoskeleton coupled with a musculoskeletal model via deep reinforcement learning," 2023
21. arXiv, "A Reinforcement Learning Based Controller to Minimize Forces on the Crutches of a Lower-Limb Exoskeleton," 2024, https://arxiv.org/abs/2402.00135
22. Just-Auto, "Hyundai Motor Group launches Vest EXoskeleton for plant workers," September 2019
23. German Bionic, Apogee and Cray X product information, https://www.germanbionic.com
24. Exoskeleton Report, "Sarcos Technology and Robotics Corporation Acquires RE2 but Delays Guardian XO Beta," April 2022; Sarcos / Palladyne AI corporate communications, 2024
25. Lockheed Martin press release, "ONYX Exoskeleton wins Popular Science Best of What's New," 2018; Breaking Defense, "Lockheed, Army To Test Exoskeleton In December"
26. Harvard Biodesign Lab, Soft Exosuits research, https://biodesign.seas.harvard.edu/soft-exosuits
27. Nature Medicine, Walsh et al., soft exosuit study on Parkinson's disease freezing of gait, 2024; Harvard Gazette, "Robotic exosuit gives Parkinson's patient smoother stride," January 2024
28. TechCrunch, "Ottobock set to acquire fellow robotic exoskeleton maker SuitX," November 2, 2021
29. Fortune Business Insights, MarketsAndMarkets, Grand View Research, Mordor Intelligence, Straits Research, FactMR, exoskeleton and wearable robotics market reports, 2025
30. Nature, Slade, P., Kochenderfer, M. J., Delp, S. L. and Collins, S. H., "Personalizing exoskeleton assistance while walking in the real world," vol. 610, 13 October 2022, https://www.nature.com/articles/s41586-022-05191-1; PubMed 36224415
31. Stanford Report / Stanford University School of Engineering, "Exoskeleton makes walking faster, less tiring" and "Untethered exoskeleton walks out into the real world," October 2022, https://news.stanford.edu/stories/2022/10/exoskeleton-makes-walking-faster-less-tiring