# Staged Multi-Agent Training (SMAT) for Hip Exoskeletons: Metabolic and Biomechanical Validation of a Simulation-Trained Co-Adaptive Controller

arXiv: https://arxiv.org/abs/2608.00715 · HTML: https://mlsanity.com/paper/2608.00715/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 27 references that are in the map.
- First posted on arXiv 1 Aug 2026.

## Builds on (most cited first, 6 of 6)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Exo-Plore: Exploring Exoskeleton Control Space through Human-aligned Simulation](https://mlsanity.com/paper/2601.22550/) (2026)
- [Reinforcement-Learning-Based Assistance Reduces Squat Effort with a Modular Hip--Knee Exoskeleton](https://mlsanity.com/paper/2602.17794/) (2026)
- [Gait Asymmetry from Unilateral Weakness and Improvement With Ankle Assistance: a Reinforcement Learning based Simulation Study](https://mlsanity.com/paper/2602.18862/) (2026)
- [Learning Hip Exoskeleton Control Policy via Predictive Neuromusculoskeletal Simulation](https://mlsanity.com/paper/2603.04166/) (2026)
- [SMAT: Staged Multi-Agent Training for Co-Adaptive Exoskeleton Control](https://mlsanity.com/paper/2603.07618/) (2026)

## Built on by (most cited first, 1 of 1)

- [UniExo: Unified Multi-Skill Policies for Musculoskeletal Locomotion and Co-Adaptive Exoskeleton Control](https://mlsanity.com/paper/2609.19690/) (2026)

## Abstract (arXiv)

Learning-based controllers can deliver exoskeleton assistance after training entirely in physics-based simulation, yet few controllers that address human-device co-adaptation have been validated on real users by whole-body metabolic measurement, the standard benchmark for assistive walking. Co-adaptation is challenging: as the device alters joint dynamics, the wearer reorganizes neuromuscular coordination, producing a non-stationary learning problem. Staged Multi-Agent Training (SMAT), a four-stage curriculum that progressively trains a musculoskeletal human actor and a bilateral hip exoskeleton actor, was introduced and shown to reduce simulated hip-muscle activation and provide positive assistance on hardware. This article provides the first physiological validation of SMAT. The policy was deployed on a hip exoskeleton and tested with eight healthy adults, with metabolic cost measured by indirect calorimetry across no-exoskeleton, passive, and active conditions. Active assistance lowered net metabolic rate by 19.7% relative to the passive device (p < 0.001). Biomechanical analysis confirmed predominantly positive hip mechanical power across all subjects (positive-power ratio 0.98), and the policy generalized across walking speeds and terrains. Together, these results show that a single simulation-trained SMAT policy, deployed without subject-specific retraining, delivers a significant metabolic benefit on real users while remaining robust beyond the conditions it was trained on.