English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The light and soft characteristics of Buoyancy Assisted Lightweight LeggedUnit (BALLU) robots have a great potential to provide intrinsically safeinteractions in environments involving humans, unlike many heavy and rigidrobots. However, their unique and sensitive dynamics impose challenges toobtaining robust control policies in the real world. In this work, wedemonstrate robust sim-to-real transfer of control policies on the BALLU robotsvia system identification and our novel residual physics learning method,Environment Mimic (EnvMimic). First, we model the nonlinear dynamics of theactuators by collecting hardware data and optimizing the simulation parameters.Rather than relying on standard supervised learning formulations, we utilizedeep reinforcement learning to train an external force policy to matchreal-world trajectories, which enables us to model residual physics withgreater fidelity. We analyze the improved simulation fidelity by comparing thesimulation trajectories against the real-world ones. We finally demonstratethat the improved simulator allows us to learn better walking and turningpolicies that can be successfully deployed on the hardware of BALLU.

Residual Physics Learning and System Identification for Sim-to-real Transfer of Policies on Buoyancy Assisted Legged Robots