Research Analyzer
← Back ICRA 2026

PRRTC: GPU-Parallel RRT-Connect for Fast, Consistent, and Low-Cost Motion Planning

Chih H. Huang, Pranav Jadhav, Brian Plancher, Zachary Kingston

PDF

AI summary

Key figure (auto-extracted from paper)
pRRTC accelerates RRT-Connect motion planning by up to 10× on GPUs through co-designed parallelism, delivering sub-millisecond, consistent, and low-cost paths for high-DOF robots.
GPU acceleration RRT-Connect motion planning parallel computing robotics collision checking

Problem

Sampling-based planners like RRT-Connect face severe computational bottlenecks in high-dimensional or cluttered environments. Existing parallel approaches only target a single level of parallelism, limiting performance on modern GPUs.

Approach

pRRTC co-designs GPU parallelism across multiple levels, running concurrent planning iterations alongside SIMT-optimized nearest-neighbor search and collision checking with efficient memory management.

Key results

  • Up to 10× speedup on constrained reaching tasks
  • 5.4× reduction in planning time standard deviation
  • 1.4× reduction in average initial path cost
  • Real-time collision-free planning demonstrated on a 14-DoF dual Franka Panda arm

Why it matters

Enables reliable, real-time motion planning for complex high-DOF robots, bridging the gap between sampling-based algorithms and dynamic real-world deployment.

Abstract

Sampling-based motion planning algorithms, like the Rapidly-Exploring Random Tree (RRT) and its widely used variant, RRT-Connect, provide efficient solutions for high- dimensional planning problems faced by real-world robots. However, these methods remain computationally intensive, par- ticularly in complex environments that require many collision checks. To improve performance, recent efforts have explored parallelizing specific components of RRT such as collision checking, or running multiple planners independently. However, little has been done to develop an integrated parallelism approach, co-designed for large-scale parallelism. In this work we present pRRTC, a RRT-Connect based planner co-designed for GPU acceleration across the entire algorithm through parallel expansion and SIMT-optimized collision checking. We evaluate the effectiveness of pRRTC on the MotionBenchMaker dataset using robots with 7, 8, and 14 degrees of freedom (DoF). Compared to the state-of-the-art, pRRTC achieves as much as a 10× speedup on constrained reaching tasks with a 5.4× reduction in standard deviation. pRRTC also achieves a 1.4× reduction in average initial path cost. Finally, we deploy pRRTC on a 14-DoF dual Franka Panda arm setup and demonstrate real-time, collision-free motion planning with dynamic obstacles. We open-source our planner to support the wider community.

Index terms

Motion and Path Planning Collision Avoidance

Related papers