Research Analyzer
← Back ICRA 2026

Learning Neural Observer-Predictor Models for Limb-Level Sampling-Based Locomotion Planning

Abhijeet Mangesh Kulkarni, Ioannis Poulakakis, Guoquan (Paul) Huang

PDF

AI summary

Key figure (auto-extracted from paper)
A provably stable neural observer-predictor framework accurately forecasts full-body legged robot motion from proprioceptive data, enabling safe, limb-level collision-aware planning in cluttered environments.
Legged robots Neural observer-predictor Full-body motion prediction Sampling-based planning MPPI Limb-level collision checking

Problem

Simplified kinematic models fail to capture the complex closed-loop dynamics of legged robots, leading to inaccurate predictions and unsafe planning in cluttered environments, while existing data-driven methods often lack full-body prediction or require environment-specific retraining.

Approach

The authors design a decoupled neural architecture that uses a stability-guaranteed observer to estimate latent states from proprioceptive history, which initializes a GRU-based predictor to rapidly generate thousands of parallel full-body trajectory rollouts for sampling-based planners.

Key results

  • Provable Uniformly Ultimately Bounded stability guarantees for the neural observer
  • GRU predictor enabling 1000 parallel trajectory rollouts in 13ms
  • Seamless integration with MPPI planner for limb-level collision checking
  • Hardware validation on a Vision60 quadruped demonstrating accurate prediction and safe navigation in narrow passages

Why it matters

Provides a robust, real-time foundation for safe autonomous navigation of dynamic legged robots in complex environments without relying on overly conservative kinematic approximations.

Abstract

Accurate full-body motion prediction is essential for the safe, autonomous navigation of legged robots, enabling critical capabilities like limb-level collision checking in cluttered environments. Simplified kinematic models often fail to capture the complex, closed-loop dynamics of the robot and its low-level controller, limiting their predictions to simple planar motion. To address this, we present a learning-based observer-predictor framework that accurately predicts this motion. Our method features a neural observer with provable Uniformly Ultimately Bounded (UUB) guarantees that provides a reliable latent state estimate from a history of proprioceptive measurements. This stable estimate initializes a computationally efficient predic- tor, designed for the rapid, parallel evaluation of thousands of potential trajectories required by modern sampling-based planners. We validated the system by integrating our neural predictor into an Model Predictive Path Integral (MPPI)- based planner on a Vision60 quadruped. Hardware experi- ments successfully demonstrated effective, limb-aware motion planning in a challenging, narrow passage and over small objects, highlighting our system’s ability to provide a robust foundation for high-performance, collision-aware planning on dynamic robotic platforms.

Index terms

Motion and Path Planning Collision Avoidance Machine Learning for Robot Control

Related papers