A Cross-Environment and Cross-Embodiment Path Planning Framework via a Conditional Diffusion Model

2025-10-21

AI Summary

To address poor generalization, high computational cost, and weak safety guarantees in robot path planning for high-dimensional complex environments, this paper proposes GADGET—a zero-shot path planning framework based on conditional diffusion models. Its core innovation is a hybrid dual-guidance mechanism: integrating classifier-free guidance for voxelized scene encoding with control barrier function (CBF)-based safety constraints to jointly enable environment-aware planning and real-time collision avoidance during denoising. GADGET supports zero-shot transfer across diverse robot morphologies (Franka Panda, Kinova Gen3, UR5) and unseen environments (spherical obstacles, picking bins, shelving units), requiring neither fine-tuning nor retraining. Experiments demonstrate high trajectory success rates, low collision rates, and successful deployment on a real Kinova Gen3 robotic platform.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Path planning for a robotic system in high-dimensional cluttered environments needs to be efficient, safe, and adaptable for different environments and hardware. Conventional methods face high computation time and require extensive parameter tuning, while prior learning-based methods still fail to generalize effectively. The primary goal of this research is to develop a path planning framework capable of generalizing to unseen environments and new robotic manipulators without the need for retraining. We present GADGET (Generalizable and Adaptive Diffusion-Guided Environment-aware Trajectory generation), a diffusion-based planning model that generates joint-space trajectories conditioned on voxelized scene representations as well as start and goal configurations. A key innovation is GADGET's hybrid dual-conditioning mechanism that combines classifier-free guidance via learned scene encoding with classifier-guided Control Barrier Function (CBF) safety shaping, integrating environment awareness with real-time collision avoidance directly in the denoising process. This design supports zero-shot transfer to new environments and robotic embodiments without retraining. Experimental results show that GADGET achieves high success rates with low collision intensity in spherical-obstacle, bin-picking, and shelf environments, with CBF guidance further improving safety. Moreover, comparative evaluations indicate strong performance relative to both sampling-based and learning-based baselines. Furthermore, GADGET provides transferability across Franka Panda, Kinova Gen3 (6/7-DoF), and UR5 robots, and physical execution on a Kinova Gen3 demonstrates its ability to generate safe, collision-free trajectories in real-world settings.

Problem

• Develops generalizable path planning for unseen environments and robots
• Reduces computation time and parameter tuning in robotic planning
• Integrates environment awareness with real-time collision avoidance

Innovation

• Diffusion model generates joint-space trajectories from voxel scenes
• Hybrid dual-conditioning integrates environment awareness with safety
• Zero-shot transfer across environments and robotic embodiments