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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

While deep reinforcement learning (RL) agents have demonstrated incrediblepotential in attaining dexterous behaviours for robotics, they tend to makeerrors when deployed in the real world due to mismatches between the trainingand execution environments. In contrast, the classical robotics community havedeveloped a range of controllers that can safely operate across most states inthe real world given their explicit derivation. These controllers however lackthe dexterity required for complex tasks given limitations in analyticalmodelling and approximations. In this paper, we propose Bayesian ControllerFusion (BCF), a novel uncertainty-aware deployment strategy that combines thestrengths of deep RL policies and traditional handcrafted controllers. In thisframework, we can perform zero-shot sim-to-real transfer, where our uncertaintybased formulation allows the robot to reliably act within out-of-distributionstates by leveraging the handcrafted controller while gaining the dexterity ofthe learned system otherwise. We show promising results on two real-worldcontinuous control tasks, where BCF outperforms both the standalone policy andcontroller, surpassing what either can achieve independently. A supplementaryvideo demonstrating our system is provided at https://bit.ly/bcf_deploy.

Zero-Shot Uncertainty-Aware Deployment of Simulation Trained Policies on Real-World Robots