Trossen Weekly Machine Learning Digest 10/25/2024

Here are some highlights from this past week in Robotics and Machine Learning:

Free Resource - Princeton University free course, Foundations of Reinforcement Learning: https://www.youtube.com/playlist?list=PLYXvCE1En13epbogBmgafC_Yyyk9oQogl

Whitepaper - ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback: ARCap: Collecting High-quality Human Demonstrations for Robot Learning with Augmented Reality Feedback

Whitepaper - Deep Visual Odometry with Events and Frames: [2309.09947] Deep Visual Odometry with Events and Frames

Whitepaper - TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports: [2410.17785] TranSPORTmer: A Holistic Approach to Trajectory Understanding in Multi-Agent Sports

Whitepaper - Integrating Reinforcement Learning with Foundation Models for Autonomous Robotics: Methods and Perspectives: [2410.16411] Integrating Reinforcement Learning with Foundation Models for Autonomous Robotics: Methods and Perspectives

Whitepaper - Learning Smooth Humanoid Locomotion
through Lipschitz-Constrained Policies: https://lipschitz-constrained-policy.github.io/

Whitepaper - Verifiably Following Complex Robot Instructions with Foundation Models: Verifiably Following Complex Robot Instructions with Foundation Models

Whitepaper - Robust Continuous Motion Strategy Against Muscle Rupture using Online Learning of Redundant Intersensory Networks for Musculoskeletal Humanoids: [2409.14951] Robust Continuous Motion Strategy Against Muscle Rupture using Online Learning of Redundant Intersensory Networks for Musculoskeletal Humanoids

Whitepaper - CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning: CCIL: Continuity-based Data Augmentation for Corrective Imitation Learning

Whitepaper - BUMBLE. Unifying Reasoning and Acting with VLMs for Building-Wide Mobile Manipulation: BUMBLE: Unifying Reasoning and Acting with VLMs for Building-Wide Mobile Manipulation

Whitepaper - Multimodal Active Measurement for Human Mesh Recovery in Close Proximity: [2310.08116] Multimodal Active Measurement for Human Mesh Recovery in Close Proximity

Whitepaper - Steering Your Generalists:
Improving Robotic Foundation Models via Value Guidance: V-GPS: Value-Guided Policy Steering

Whitepaper - Physics-informed Neural Mapping and Motion Planning in Unknown Environments: [2410.09883] Physics-informed Neural Mapping and Motion Planning in Unknown Environments