Teleoperator-Aware and Safety-Critical Adaptive Nonlinear MPC for Shared Autonomy in Obstacle Avoidance of Legged Robots

2025-09-26

AI Summary

To address insufficient safety and adaptability in shared control for quadrupedal robot teleoperation, this paper proposes a hierarchical safety-critical shared control framework. At the low level, a 500-Hz quadratic-programming (QP)-based whole-body dynamics controller ensures real-time torque tracking. At the mid level, a 60-Hz adaptive nonlinear model predictive controller (MPC) optimizes reference trajectories. At the high level, human intent and autonomous obstacle avoidance are fused at 10 Hz. A novel noise-rational Boltzmann model estimates operator intent online, while a variable-gradient projection method dynamically adjusts human–robot arbitration weights. Forward safety is explicitly guaranteed via control barrier functions (CBFs). Experimental validation on the Unitree Go2 platform demonstrates millisecond-level real-time obstacle avoidance and intent-adaptive learning in complex environments. User studies confirm significant improvements in collaborative safety and control effectiveness.

Technology Category

• Intelligent Robots: Behavior Learning & Control
• Natural Language Processing: Safety and Robustness
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Ensuring safe and effective collaboration between humans and autonomous legged robots is a fundamental challenge in shared autonomy, particularly for teleoperated systems navigating cluttered environments. Conventional shared-control approaches often rely on fixed blending strategies that fail to capture the dynamics of legged locomotion and may compromise safety. This paper presents a teleoperator-aware, safety-critical, adaptive nonlinear model predictive control (ANMPC) framework for shared autonomy of quadrupedal robots in obstacle-avoidance tasks. The framework employs a fixed arbitration weight between human and robot actions but enhances this scheme by modeling the human input with a noisily rational Boltzmann model, whose parameters are adapted online using a projected gradient descent (PGD) law from observed joystick commands. Safety is enforced through control barrier function (CBF) constraints integrated into a computationally efficient NMPC, ensuring forward invariance of safe sets despite uncertainty in human behavior. The control architecture is hierarchical: a high-level CBF-based ANMPC (10 Hz) generates blended human-robot velocity references, a mid-level dynamics-aware NMPC (60 Hz) enforces reduced-order single rigid body (SRB) dynamics to track these references, and a low-level nonlinear whole-body controller (500 Hz) imposes the full-order dynamics via quadratic programming to track the mid-level trajectories. Extensive numerical and hardware experiments, together with a user study, on a Unitree Go2 quadrupedal robot validate the framework, demonstrating real-time obstacle avoidance, online learning of human intent parameters, and safe teleoperator collaboration.

Problem

• Developing safe shared autonomy for human-robot collaboration in legged robots
• Overcoming limitations of fixed blending strategies in dynamic environments
• Ensuring real-time obstacle avoidance while adapting to human intent

Innovation

• Adaptive nonlinear MPC with online human intent learning
• Hierarchical control with CBF safety constraints
• Real-time obstacle avoidance for quadrupedal robots