CANVAS: Commonsense-Aware Navigation System for Intuitive Human-Robot Interaction

TL;DR

CANVAS is a novel framework that combines visual and linguistic instructions with imitation learning to enable robots to navigate intuitively based on abstract human cues, outperforming traditional rule-based systems especially in noisy and unseen environments.

Contribution

This paper introduces CANVAS, a new commonsense-aware navigation system that integrates visual and linguistic instructions and leverages imitation learning, along with a comprehensive dataset COMMAND, to improve robot navigation in complex scenarios.

Findings

CANVAS outperforms ROS NavStack across various environments.

Achieves 67% success in orchard environment where ROS NavStack fails.

Demonstrates effective Sim2Real transfer with 69% success rate.

Abstract

Real-life robot navigation involves more than just reaching a destination; it requires optimizing movements while addressing scenario-specific goals. An intuitive way for humans to express these goals is through abstract cues like verbal commands or rough sketches. Such human guidance may lack details or be noisy. Nonetheless, we expect robots to navigate as intended. For robots to interpret and execute these abstract instructions in line with human expectations, they must share a common understanding of basic navigation concepts with humans. To this end, we introduce CANVAS, a novel framework that combines visual and linguistic instructions for commonsense-aware navigation. Its success is driven by imitation learning, enabling the robot to learn from human navigation behavior. We present COMMAND, a comprehensive dataset with human-annotated navigation results, spanning over 48 hours and 219 km, designed to train commonsense-aware navigation systems in simulated environments. Our experiments show that CANVAS outperforms the strong rule-based system ROS NavStack across all environments, demonstrating superior performance with noisy instructions. Notably, in the orchard environment, where ROS NavStack records a 0% total success rate, CANVAS achieves a total success rate of 67%. CANVAS also closely aligns with human demonstrations and commonsense constraints, even in unseen environments. Furthermore, real-world deployment of CANVAS showcases impressive Sim2Real transfer with a total success rate of 69%, highlighting the potential of learning from human demonstrations in simulated environments for real-world applications.