Fibration trees unify projections and decompositions for multi-robot planning; Fibration-RRT generalizes quotient and discrete RRT, is probabilistically complete, and solves problems up to 96 DOF via user-defined trees.
Simultaneous multi-robot motion planning with projected diffusion models
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
representative citing papers
Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.
MADP uses diffusion models to generate interdependent actions for decentralized robot swarms in coverage control, trained via imitation from a clairvoyant expert and shown to generalize and outperform baselines across varying agent densities and importance densities.
A constrained optimization framework for diffusion model unlearning via KL and likelihood constraints, with duality results and reported better retention-unlearning tradeoffs than weight-based baselines.
Adaptive correction scheduling for hard constraints in generative sampling recovers 71% of stepwise projection benefits using 75% fewer corrections by focusing on trajectory-perturbing steps.
A diffusion-based multi-robot planner trained on few agents generalizes to larger numbers during deployment using inter-agent attention and temporal convolution.
A flow-matching generator plus a learned warm-started safety filter plans collision-free trajectories for tens of robots in tens of milliseconds, with batched multi-instance support.
Presents initial design and first prototypes of robotic optical-relay positioners addressing ELT-scale challenges of relay optics, pupil pointing, and per-positioner ADCs for the MOSAIC instrument.
A focal plate prototype for Stage-5 telescope instruments shows that 5-axes machining can achieve the required tilt and focus tolerances.
Thermal qualification tests on 6.2-mm-pitch fiber positioners confirm stable repeatability, backlash, and linearity across -20°C to 30°C with no degradation.
citing papers explorer
-
Fibration Trees: A Unified Approach to Multi-Robot Motion Planning
Fibration trees unify projections and decompositions for multi-robot planning; Fibration-RRT generalizes quotient and discrete RRT, is probabilistically complete, and solves problems up to 96 DOF via user-defined trees.
-
Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling
Constraint-Aware Flow Matching integrates constraint projections into the flow matching training objective to align model dynamics with constrained sampling and reduce distributional shift.
-
Scalable Multi Agent Diffusion Policies for Coverage Control
MADP uses diffusion models to generate interdependent actions for decentralized robot swarms in coverage control, trained via imitation from a clairvoyant expert and shown to generalize and outperform baselines across varying agent densities and importance densities.
-
Unlearning in Diffusion Models: A Unified Framework with KL Divergence and Likelihood Constraints
A constrained optimization framework for diffusion model unlearning via KL and likelihood constraints, with duality results and reported better retention-unlearning tradeoffs than weight-based baselines.
-
Enforcing Constraints in Generative Sampling via Adaptive Correction Scheduling
Adaptive correction scheduling for hard constraints in generative sampling recovers 71% of stepwise projection benefits using 75% fewer corrections by focusing on trajectory-perturbing steps.
-
Train-Small Deploy-Large: Leveraging Diffusion-Based Multi-Robot Planning
A diffusion-based multi-robot planner trained on few agents generalizes to larger numbers during deployment using inter-agent attention and temporal convolution.
-
Flow-Opt: Scalable Centralized Multi-Robot Trajectory Optimization with Flow Matching and Differentiable Optimization
A flow-matching generator plus a learned warm-started safety filter plans collision-free trajectories for tens of robots in tens of milliseconds, with batched multi-instance support.
-
MOSAIC at ELT: Design and First Prototyping of Novel Robotic Optical-Relay Positioners
Presents initial design and first prototypes of robotic optical-relay positioners addressing ELT-scale challenges of relay optics, pupil pointing, and per-positioner ADCs for the MOSAIC instrument.
-
Focal Plate Prototyping for Modular Focal Planes of Stage-5 Instruments For Ground-Based Telescopes
A focal plate prototype for Stage-5 telescope instruments shows that 5-axes machining can achieve the required tilt and focus tolerances.
-
Thermal Characterization of a 6-Positioner, 6.2-mm-Pitch Module for Stage-5 Telescopes
Thermal qualification tests on 6.2-mm-pitch fiber positioners confirm stable repeatability, backlash, and linearity across -20°C to 30°C with no degradation.