• EG-RRT: Environment-guided random trees for kinodynamic motion planning with uncertainty and obstacles 

      Jaillet, Leonard Georges; Hoffman, Judy; Van den Berg, Jur; Abbeel, Pieter; Porta Pleite, Josep Maria; Goldberg, Ken (2011)
      Text en actes de congrés
      Accés obert
      Existing sampling-based robot motion planning methods are often inefficient at finding trajectories for kinodynamic systems, especially in the presence of narrow passages between obstacles and uncertainty in control and ...
    • Self-supervised policy adaptation during deployment 

      Hansen, Nicklas; Jangir, Rishabh; Alenyà Ribas, Guillem; Abbeel, Pieter; Efros A, Alexei; Pinto, Lerrel; Wang, Xiaolong (OpenReview.net, 2021)
      Text en actes de congrés
      Accés obert
      In most real world scenarios, a policy trained by reinforcement learning in one environment needs to be deployed in another, potentially quite different environment. However, generalization across different environments ...