Reactive Stepping for Humanoid Robots using Reinforcement Learning: Application to Standing Push Recovery on the Exoskeleton Atalante

Duburcq, Alexis; Schramm, Fabian; Boéris, Guilhem; Bredèche, Nicolas; Chevaleyre, Yann

doi:10.1109/iros47612.2022.9982234

Cited by 3 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The last balance recovery strategy is the stepping-strategy, which is not implemented in the current controller but will be our next priority. This strategy is very effective and can deal with much stronger pushes than the ones rejected in this work [8]. We have demonstrated that the LLE can self-balance in three different double stance poses, which are contact scenarios that arise while traversing terrain.…”

Section: Limitations Comparison and Enhancementsmentioning

confidence: 81%

“…In contrast, Atalante achieves balance during stance [8] and dynamically balanced gaits at speeds of 0.3 m/s (forward and backward) and consists of six actuated joints per leg: Hip rotation, abduction and flexion, knee flexion, ankle flexion, and inversion. The reported walking high-level controller of this LLE [9] computes joint trajectories that result in dynamic walking motion using the partial Hybrid Zero Dynamics (HZD) approach.…”

Section: A State Of the Art In Lle Balance Controlmentioning

confidence: 99%

“…The reported walking high-level controller of this LLE [9] computes joint trajectories that result in dynamic walking motion using the partial Hybrid Zero Dynamics (HZD) approach. In [8], a control policy that prescribes joint velocities to recover balance is trained with reinforcement learning. These methods are effective but require actuation in the 6 joints per leg of the LLE, while most exoskeletons do not have this amount of (actuated) degrees of freedom.…”

Section: A State Of the Art In Lle Balance Controlmentioning

confidence: 99%

See 2 more Smart Citations

Implementation and Tuning of Momentum-Based Controller for Standing Balance in a Lower-limb Exoskeleton with Paraplegic User

Prieto,

Keemink,

Asseldonk

et al. 2024

Preprint

View full text Add to dashboard Cite

Lower limb exoskeletons (LLEs) are wearable devices that can restore the movement autonomy of paraplegic users. LLEs can restore the users’ ability to stand upright and walk. However, most of the commercially available and clinically used LLEs rely on the user maintaining balance through the use of crutches. Recent improvements in the design and control of LLEs and other legged robots allow for autonomous balance control. In this work, we implement and evaluate a momentum-based standing balance controller in the Symbitron LLE, consisting of eight active (torque-controlled) and two passive joints. We first investigate how gain tuning of the center of mass tracking control law, part of a multi-task optimal controller, affects balancing performance. We apply pushes on different device locations while in parallel-stance, compare the response for different gains, and derive heuristic guidelines for controller tuning given the control architecture, high-level goals, and hardware limitations. Next, we show how this controller successfully prescribes joint torques to the LLE to maintain balance with a paraplegic user. The LLE can autonomously balance the user and reject mediolateral and anteroposterior pushes in the order of 60 N at hip height (and 40 N at shoulder height) while standing in parallel-stance, staggered-stance with both feet at the same height, and staggered-stance with a height difference of 0.05 m between the feet. This work presents a viable control strategy for torque-controlled light-weight under-actuated LLEs to keep the balance of paraplegic users during stance, which is a necessary starting point towards autonomous balance control during gait.

show abstract

Section: Limitations Comparison and Enhancementsmentioning

confidence: 81%

Section: A State Of the Art In Lle Balance Controlmentioning

confidence: 99%