MIMIC-D enables multi-modal multi-agent coordination via joint training of decentralized diffusion policies using only local information.
hub
Diffusion policy: Visuomotor policy learning via ac- tion diffusion
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
hub tools
representative citing papers
HITL-D combines diffusion policies with human input for shared robotic control, reducing required joystick axes and improving speed and workload in manipulation tasks per a 12-participant study.
Introduces a directed graphical abstraction for topple actions in stack rearrangement, reducing planning to a pebble motion variant and showing faster execution in simulation than pick-and-place alone.
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.
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.
HardFlow turns hard constraint enforcement during flow-matching sampling into a tractable terminal-time trajectory optimization problem using optimal control.
LACY is a VLM framework jointly trained on L2A, A2L, and L2C tasks that uses an active augmentation cycle to self-improve robotic manipulation policies, reporting a 56.46% average success rate gain in simulation and real-world experiments.
COMPASS is a manipulation-aware active sensing framework that raises simulated manipulation success rates by 24.25% over information-gain-only baselines in a new four-level confined-space benchmark.
A diffusion policy learns coordinated control of a mobile base and dual arms to open and traverse damped pull doors in a single end-to-end visuomotor model.
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
-
MIMIC-D: Multi-modal Imitation for MultI-agent Coordination with Decentralized Diffusion Policies
MIMIC-D enables multi-modal multi-agent coordination via joint training of decentralized diffusion policies using only local information.
-
HITL-D: Human In The Loop Diffusion Assisted Shared Control
HITL-D combines diffusion policies with human input for shared robotic control, reducing required joystick axes and improving speed and workload in manipulation tasks per a 12-participant study.
-
Virtues of Ordered Chaos: Planning with Topple Actions in Tabletop Stack Rearrangement
Introduces a directed graphical abstraction for topple actions in stack rearrangement, reducing planning to a pebble motion variant and showing faster execution in simulation than pick-and-place alone.
-
Refinement of Accelerated Demonstrations via Incremental Iterative Reference Learning Control for Fast Contact-Rich Imitation Learning
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.
-
ESPADA: Execution Speedup via Semantics Aware Demonstration Data Downsampling for Imitation Learning
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.
-
HardFlow: Hard-Constrained Sampling for Flow-Matching Models via Trajectory Optimization
HardFlow turns hard constraint enforcement during flow-matching sampling into a tractable terminal-time trajectory optimization problem using optimal control.
-
LACY: A Vision-Language Model-based Language-Action Cycle for Self-Improving Robotic Manipulation
LACY is a VLM framework jointly trained on L2A, A2L, and L2C tasks that uses an active augmentation cycle to self-improve robotic manipulation policies, reporting a 56.46% average success rate gain in simulation and real-world experiments.
-
COMPASS: Confined-space Manipulation Planning with Active Sensing Strategy
COMPASS is a manipulation-aware active sensing framework that raises simulated manipulation success rates by 24.25% over information-gain-only baselines in a new four-level confined-space benchmark.
-
Diffusion Policy for Coordinated Control of a Nonholonomic Mobile Base and Dual Arms in Door Opening and Passing
A diffusion policy learns coordinated control of a mobile base and dual arms to open and traverse damped pull doors in a single end-to-end visuomotor model.
-
Flow with the Force Field: Learning 3D Compliant Flow Matching Policies from Force and Demonstration-Guided Simulation Data
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.