Trossen Weekly Machine Learning Digest 11/1/2024

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

News - China launches data-sharing initiative for humanoid developers: China launches data-sharing initiative for humanoid developers

Whitepaper and Article - Advancing embodied AI through progress in touch perception, dexterity, and human-robot interaction [META]: Advancing embodied AI through progress in touch perception, dexterity, and human-robot interaction

Whitepaper - π0: A Vision-Language-Action Flow Model for
General Robot Control: Our First Generalist Policy | https://www.π.com/download/pi0.pdf

Whitepaper - Harmon: Whole-Body Motion Generation of Humanoid Robots from Language Descriptions: Harmon

Whitepaper - Learning Robotic Manipulation Policies from Point Clouds with Conditional Flow Matching: http://pointflowmatch.cs.uni-freiburg.de/

Whitepaper - Local Policies Enable Zero-shot Long Horizon Manipulation: ManipGen

Whitepaper - RoPotter: Toward Robotic Pottery and Deformable Object Manipulation with Structural Priors: https://robot-pottery.github.io/

Whitepaper - Adaptive Complexity Model Predictive Control: Adaptive Complexity Model Predictive Control | IEEE Journals & Magazine | IEEE Xplore

Whitepaper - RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation: RDT-1B: a Diffusion Foundation Model for Bimanual Manipulation

Whitepaper - Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation: [2410.04855] Unsupervised Skill Discovery for Robotic Manipulation through Automatic Task Generation

Whitepaper - Neural Fields in Robotics: A Survey: [2410.20220] Neural Fields in Robotics: A Survey

Whitepaper - SkillMimicGen: Automated Demonstration Generation for Efficient Skill Learning and Deployment: https://skillgen.github.io/

Whitepaper - Robust High-Speed State Estimation for Off-road
Navigation using Radar Velocity Factors: https://arxiv.org/pdf/2409.10953

Whitepaper - ROAMER: Robust Offroad Autonomy using Multimodal
State Estimation with Radar Velocity Integration: https://arxiv.org/pdf/2401.17404

Whitepaper - Paper Notes: Building-Wide Mobile Manipulation: Paper Notes: Building-Wide Mobile Manipulation

Whitepaper - Data Scaling Laws in Imitation Learning for Robotic Manipulation: https://data-scaling-laws.github.io/

Whitepaper - Diffusing States and Matching Scores: A New Framework for Imitation Learning: [2410.13855] Diffusing States and Matching Scores: A New Framework for Imitation Learning

1 Like