Accelerating Human-Aware Robot Trajectory Generation via Diffusion and Consistency Distillation

2026-08-04

AI Summary

This work addresses the challenge of generating safe and smooth trajectories for non-redundant robotic arms in human-robot interaction, where simultaneously satisfying end-effector pose, obstacle avoidance, and self-collision constraints is difficult. The authors propose the first approach integrating diffusion models with consistency distillation for this task: a dataset of constraint-compliant trajectories is first generated using RRT/RRT*, which is then used to train a diffusion model capable of producing valid trajectories via guided sampling. Consistency distillation further accelerates inference to under 100 milliseconds for generating 150 candidate trajectories, while a novel joint-weighted jerk regularization significantly enhances trajectory smoothness. The method achieves high task success rates while substantially reducing both inference latency and jerk at both joints and the end-effector.

Abstract

This research proposes a constrained motion planning framework for robot manipulators in human-robot interaction (HRI). For a non-redundant manipulator with a fully specified end-effector pose, additional requirements such as collision avoidance and self-collision avoidance are difficult to handle as simple null-space secondary tasks. This limitation makes it challenging to generate feasible joint-space trajectories in HRI environments where safety and kinematic constraints must be considered simultaneously. To address this limitation, collision- and self-collision-aware trajectories are generated using Rapidly-exploring Random Tree (RRT) and RRT* algorithms, and the resulting dataset is used to train a diffusion model that generates constraint-satisfying trajectories through guided sampling. To reduce the inference time required for iterative diffusion sampling, consistency distillation is applied, and a joint-weighted jerk regularization term is incorporated into the loss function to promote smoother trajectories by penalizing abrupt changes in joint acceleration. Simulation results show that the consistency model generates 150 trajectory candidates in less than 100 ms, maintains a high episode success rate, and substantially reduces joint and end-effector jerk when jerk regularization is applied.

Problem

• human-robot interaction
• collision avoidance
• trajectory generation
• kinematic constraints
• joint-space planning

Innovation

• diffusion model
• consistency distillation
• trajectory generation
• human-robot interaction
• jerk regularization