FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning

FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning

FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learning FACTR : F orce- A ttending C urriculum Tr aining for Contact-Rich Policy Learning Jason Jingzhou Liu* Yulong Li* Kenneth Shaw Tony Tao Ruslan Salakhutdinov Deepak Pathak Jason Jingzhou Liu* Yulong Li* Kenneth Shaw Tony Tao Ruslan Salakhutdinov Deepak Pathak *Equal contribution. RSS 2025 Summary arXiv Hardware Font Awesome fontawesome.com --> Teleop Code Font Awesome fontawesome.com --> Training Code Abstract Many contact-rich tasks humans perform, such as box pickup or rolling dough, rely on force feedback for reliable

saved by

• Shiza Charania

related reading

• FACTR: Force-Attending Curriculum Training for Contact-Rich Policy Learningarxiv.org
• FORTE: Tactile Force and Slip Sensing on Compliant Fingers for Delicate Manipulationarxiv.org
• Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Controlsteerable-policies.github.io
• State of Robot Learning, December 2025vedder.io
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusiondiffusion-policy.cs.columbia.edu
• ERCEIVER-ACTOR: A Multi-Task Transformer for Robotic Manipulationarxiv.org
• Emergent Dexterity via Diverse Resets and Large-Scale Reinforcement Learningarxiv.org
• [2607.15275] RoboTTT: Context Scaling for Robot Policiesarxiv.org
• Scalable Behavior Cloning with Open Data, Training, and Evaluationabc.bot
• RoboTTT: Context Scaling for Robot Policiesresearch.nvidia.com
• Generating Robot Hands from Human Demonstrationsarxiv.org
• Learning Sim-to-Real Humanoid Locomotion in 15 Minutesyounggyo.me