CoRAL lets LLMs act as adaptive cost designers for motion planners while using VLM priors and online identification to handle unknown physics, achieving over 50% higher success rates than baselines in unseen contact-rich robotic scenarios.
Factr: Force-attending curriculum training for contact-rich policy learning
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.RO 7roles
background 1polarities
background 1representative citing papers
The paper provides a task-driven benchmark comparing visual, acoustic, magnetic, and resistive tactile sensors on three manipulation tasks and concludes that sensor utility depends on modality, material friction, and task specifics.
DexJoCo is a benchmark and toolkit with 11 functionally grounded tasks, 1.1K trajectories, and empirical benchmarks for task-oriented dexterous manipulation on MuJoCo.
Incremental Iterative Reference Learning Control refines accelerated demonstrations to achieve up to 10x faster execution in contact-rich imitation learning with 22.5% better trajectory similarity than direct IRLC and improved policy success.
SCFields fuses semantics and contact data in a sim-to-real pipeline to enable category-level generalization for tactile tool manipulation with diffusion policies.
ESPADA uses semantic segmentation from VLMs and LLMs plus DTW to downsample non-critical segments in demonstrations, delivering about 2x faster robot execution in behavior cloning while maintaining task success rates.
Framework generates force-informed sim data from one demo to train compliant visuomotor flow matching policies, showing reliable contact on real-robot block flipping and bi-manual tasks.
citing papers explorer
-
CoRAL: Contact-Rich Adaptive LLM-based Control for Robotic Manipulation
CoRAL lets LLMs act as adaptive cost designers for motion planners while using VLM priors and online identification to handle unknown physics, achieving over 50% higher success rates than baselines in unseen contact-rich robotic scenarios.