VOCALoco: Viability-Optimized Cost-aware Adaptive Locomotion

2025-10-27

AI Summary

End-to-end deep reinforcement learning suffers from poor safety guarantees, limited interpretability, and inadequate adaptability to unfamiliar terrains in legged robot locomotion control. To address these challenges, we propose VOCALoco—a hierarchical motion control framework based on modular skill selection. VOCALoco performs real-time terrain perception and jointly models the execution safety and expected transport cost (encompassing energy consumption and kinematic feasibility) of pre-trained locomotion policies, dynamically selecting the optimal policy within a receding planning horizon. Its key innovation lies in unifying safety verification and energy-efficiency prediction within a single policy evaluation mechanism, enabling safety–efficiency co-optimization. In both simulation and real-world experiments on stair climbing and descending with a quadrupedal robot, VOCALoco significantly improves locomotion robustness and safety while offering greater interpretability and deployment reliability compared to end-to-end approaches.

Technology Category

• Intelligent Robots: Learning & Optimization for ROB
• Natural Language Processing: Safety and Robustness
• Search and Optimization: Learning to Search

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
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Recent advancements in legged robot locomotion have facilitated traversal over increasingly complex terrains. Despite this progress, many existing approaches rely on end-to-end deep reinforcement learning (DRL), which poses limitations in terms of safety and interpretability, especially when generalizing to novel terrains. To overcome these challenges, we introduce VOCALoco, a modular skill-selection framework that dynamically adapts locomotion strategies based on perceptual input. Given a set of pre-trained locomotion policies, VOCALoco evaluates their viability and energy-consumption by predicting both the safety of execution and the anticipated cost of transport over a fixed planning horizon. This joint assessment enables the selection of policies that are both safe and energy-efficient, given the observed local terrain. We evaluate our approach on staircase locomotion tasks, demonstrating its performance in both simulated and real-world scenarios using a quadrupedal robot. Empirical results show that VOCALoco achieves improved robustness and safety during stair ascent and descent compared to a conventional end-to-end DRL policy

Problem

• Addresses safety limitations in legged robot locomotion generalization
• Optimizes energy-efficient policy selection for adaptive terrain traversal
• Enhances robustness in stair ascent/descent using modular control

Innovation

• Modular skill-selection framework adapting locomotion strategies dynamically
• Evaluates policy viability and energy-consumption via safety-cost prediction
• Selects safe energy-efficient policies based on local terrain observation