Research Analyzer
← Back ICRA 2026

IMPACT: Intelligent Motion Planning with Acceptable Contact Trajectories Via Vision-Language Models

Yiyang Ling, Karan Owalekar, Oluwatobiloba Adesanya, Erdem Bıyık, Daniel Seita

PDF

AI summary

Key figure (auto-extracted from paper)
IMPACT enables robots to navigate dense clutter by using VLMs to identify and execute semantically acceptable contacts.
Motion Planning Vision-Language Models Contact-Rich Manipulation Cluttered Environments Anisotropic Cost Maps

Problem

Traditional collision-free motion planning is often too restrictive in cluttered environments where some contact is necessary, but characterizing which contacts are benign versus dangerous is difficult.

Approach

The framework uses a VLM to assign semantic costs to objects and generates an anisotropic cost map encoding directional push safety for a contact-aware A* planner.

Key results

  • 78% success rate in simulation, outperforming RRT, RRT*, and LAPP
  • Lower object displacement (2.51 cm) compared to other VLM-based planners
  • Validated across 3200 simulation trials and 200 real-world trials
  • Higher human preference rankings over alternative methods

Why it matters

This allows robots to operate in highly cluttered spaces where strict collision avoidance would make tasks infeasible.

Abstract

Motion planning involves determining a sequence of robot configurations to reach a desired pose, subject to movement and safety constraints. Traditional motion planning finds collision-free paths, but this is overly restrictive in clutter, where it may not be possible for a robot to accomplish a task without contact. In addition, contacts range from relatively benign (e.g., brushing a soft pillow) to more dangerous (e.g., toppling a glass vase), making it difficult to characterize which may be acceptable. In this paper, we propose IMPACT, a novel motion planning framework that uses Vision-Language Models (VLMs) to infer environment semantics, identifying which parts of the environment can best tolerate contact based on object properties and locations. Our approach generates an anisotropic cost map that encodes directional push safety. We pair this map with a contact-aware A* planner to find stable contact-rich paths. We perform experiments using 20 simulation and 10 real-world scenes and assess using task success rate, object displacements, and feedback from human evaluators. Our results over 3200 simulation and 200 real-world trials suggest that IMPACT enables efficient contact-rich motion planning in cluttered settings while outperforming alternative methods and ablations. Our project website is available at https://impact-planning.github.io/.

Index terms

Manipulation Planning Semantic Scene Understanding AI-Enabled Robotics

Related papers