v164: Proceedings of CoRL 2021

2026-06-10 · Source: Proceedings of Machine Learning Research · Field: Technology & Digital — Robotics & Autonomous Systems, Artificial Intelligence & Machine Learning · Depth: Expert, extended

Summary

Volume 164 documents the proceedings of the 5th Conference on Robot Learning (CoRL 2021), held in London, UK, from 8-11 November, showcasing diverse advancements in robot learning. Research spans sophisticated reinforcement learning techniques for visuomotor tasks, locomotion, and multi-arm manipulation, alongside significant progress in robotic perception, including 3D scene representations and tactile sensing. The proceedings also cover innovations in robot planning, navigation in complex environments, and human-robot interaction, with a focus on learning from demonstrations and human feedback. Additionally, papers address crucial areas like safety, robustness, and the development of large-scale simulation platforms and datasets such as iGibson 2.0 and BEHAVIOR. "Blue Sky Papers" further explore foundational challenges like data-efficient RL, task specification, and achieving robot understanding through causal models.

Key takeaway

The 5th Conference on Robot Learning (CoRL 2021) presents significant progress across core areas of robotic perception, manipulation, and autonomous navigation. Key contributions include novel reinforcement learning methods for long-horizon tasks, advanced 3D scene understanding, and improved human-robot collaboration via imitation and reward learning. These insights are vital for professionals in robotics, AI, and autonomous systems seeking to develop more capable and safer real-world robot applications.

Topics

• Robot Reinforcement Learning
• Robotic Manipulation
• Robotic Perception
• Autonomous Navigation
• Human-Robot Interaction

Code references

• Data-Science-in-Mechanical-Engineering/Using-Model-Knowledge-for-Learning-Forward-Dynamics
• baceituno/dlm
• WangYueFt/detr3d
• oravus/SeqMatchNet
• AutoAILab/FusionDepth

Best for: Research Scientist, AI Scientist, Robotics Engineer, Machine Learning Engineer

Related on AIssential

• v205: Proceedings of CoRL 2022 — Volume 205 of the Conference on Robot Learning, held in December 2022, showcases significant advancements across various facets of robot learning.
• v229: Proceedings of CoRL 2023 — The 7th Conference on Robot Learning (CoRL 2023), held in Atlanta, USA, from November 6-9, 2023, showcased significant advancements in robot learning, with a strong emphasis on leveraging large langua…
• A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies — Co-training effectiveness in robotics stems from structured representation alignment and importance reweighting.
• Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty — Co-training SDCs with personality-driven MARL pedestrians significantly improves safety by exposing vehicles to realistic, uncertain human behaviors.
• Expanding Spatial and Temporal Context for Robotic Imitation Learning With Scene Graphs — Scene graphs provide explicit, compact memory for robots to reason over long-horizon tasks under partial observability.
• Intelligent Robots in 2026: Are We There Yet? [Nikita Rudin] - 760 — Bridging the sim-to-real gap and integrating semantics are critical for advanced robot autonomy and value generation.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by Proceedings of Machine Learning Research.