22 papers · 1 filter
Set-Supervised Diffusion Policy: Learning Action-Chunking Diffusion through Corrections
Zhaoting Li, Gang Chen, Javier Alonso-Mora +2
Diffusion policies have recently emerged as a powerful framework for robotic manipulation. However, like other behavior cloning methods, they remain vulnerable to distributional sh…
Active inference as a unified model of collision avoidance behavior in human drivers
Julian F. Schumann, Johan Engström, Leif Johnson +4
Collision avoidance -- involving a rapid threat detection and quick execution of the appropriate evasive maneuver -- is a critical aspect of driving. However, existing models of hu…
From Action Labels to Sets: Rethinking Action Supervision for Imitation Learning from Corrective Feedback
Zhaoting Li, Rodrigo Pérez-Dattari, Robert Babuska +2
Behavior cloning (BC) optimizes policies by treating human demonstrations as pointwise action labels. While effective with accurate action labels, this formulation is brittle in pr…
LLM-Guided Task- and Affordance-Level Exploration in Reinforcement Learning
Jelle Luijkx, Runyu Ma, Zlatan AjanoviÄ +1
Reinforcement learning (RL) is a promising approach for robotic manipulation, but it can suffer from low sample efficiency and requires extensive exploration of large state-action…
Studying the Effect of Explicit Interaction Representations on Learning Scene-level Distributions of Human Trajectories
Anna Mészáros, Javier Alonso-Mora, Jens Kober
Effectively capturing the joint distribution of all agents in a scene is relevant for predicting the true evolution of the scene and in turn providing more accurate information to…
Sequentially Teaching Sequential Tasks : Teaching Robots Long-horizon Manipulation Skills
Zlatan AjanoviÄ, Ravi Prakash, Leandro de Souza Rosa +1
Learning from demonstration has proved itself useful for teaching robots complex skills with high sample efficiency. However, teaching long-horizon tasks with multiple skills is ch…