ADMM-MCBF-LCA: A Layered Control Architecture for Safe Real-Time Navigation

2025-03-04

AI Summary

This work addresses real-time safe navigation for robots operating in dynamic environments with arbitrarily smooth-moving obstacles and input saturation constraints. We propose a hierarchical control framework: a low-level controller employing feedback linearization coupled with an offline-precomputed library of feasible controllers enables rapid response, while a high-level optimizer solves a safety-constrained optimal control problem via the Alternating Direction Method of Multipliers (ADMM), integrating Control Barrier Functions (CBFs). This architecture achieves, for the first time, tight coupling between the offline controller library and online ADMM-based CBF (ADMM-MCBF) optimization, guaranteeing both strict input feasibility and safety enforcement at 100 Hz. Evaluations in Gazebo simulation and on a physical Fetch robot demonstrate 100% safe arrival rate, zero input saturation violations, and zero safety constraint breaches—outperforming state-of-the-art hierarchical, end-to-end, and reactive approaches.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Mixed Discrete/Continuous Planning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work

Abstract

We consider the problem of safe real-time navigation of a robot in a dynamic environment with moving obstacles of arbitrary smooth geometries and input saturation constraints. We assume that the robot detects and models nearby obstacle boundaries with a short-range sensor and that this detection is error-free. This problem presents three main challenges: i) input constraints, ii) safety, and iii) real-time computation. To tackle all three challenges, we present a layered control architecture (LCA) consisting of an offline path library generation layer, and an online path selection and safety layer. To overcome the limitations of reactive methods, our offline path library consists of feasible controllers, feedback gains, and reference trajectories. To handle computational burden and safety, we solve online path selection and generate safe inputs that run at 100 Hz. Through simulations on Gazebo and Fetch hardware in an indoor environment, we evaluate our approach against baselines that are layered, end-to-end, or reactive. Our experiments demonstrate that among all algorithms, only our proposed LCA is able to complete tasks such as reaching a goal, safely. When comparing metrics such as safety, input error, and success rate, we show that our approach generates safe and feasible inputs throughout the robot execution.

Problem

• Safe real-time robot navigation in dynamic environments
• Handling input constraints and computational burden
• Ensuring safety and feasibility in robot execution

Innovation

• Layered control architecture for real-time navigation
• Offline path library with feasible controllers
• Online safe input generation at 100 Hz