UniPilot: Enabling GPS-Denied Autonomy Across Embodiments

2025-09-15

AI Summary

To address the common challenge of autonomous operation for multi-robot systems in GPS-denied environments, this paper proposes UniPilot—a compact, hardware-software co-designed autonomous payload. Methodologically, it introduces a cross-platform, full-stack autonomous system architecture integrating multimodal perception (LiDAR, radar, vision, and IMU), learning-enhanced exploratory path planning, and robust navigation control. UniPilot supports plug-and-play deployment on heterogeneous robot platforms and enables high-precision real-time mapping, active environmental exploration, and safe autonomous navigation without GNSS. Experimental results demonstrate its strong adaptability, localization stability, and task generalization capability across complex indoor and outdoor dynamic scenarios. The system significantly enhances operational autonomy for heterogeneous robots in unknown, unstructured environments.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Multilingual and cross-lingual Web search

Abstract

This paper presents UniPilot, a compact hardware-software autonomy payload that can be integrated across diverse robot embodiments to enable autonomous operation in GPS-denied environments. The system integrates a multi-modal sensing suite including LiDAR, radar, vision, and inertial sensing for robust operation in conditions where uni-modal approaches may fail. UniPilot runs a complete autonomy software comprising multi-modal perception, exploration and inspection path planning, and learning-based navigation policies. The payload provides robust localization, mapping, planning, and safety and control capabilities in a single unit that can be deployed across a wide range of platforms. A large number of experiments are conducted across diverse environments and on a variety of robot platforms to validate the mapping, planning, and safe navigation capabilities enabled by the payload.

Problem

• Enabling autonomous operation in GPS-denied environments
• Providing robust multi-modal perception and navigation capabilities
• Deploying unified autonomy payload across diverse robot platforms

Innovation

• Compact hardware-software autonomy payload
• Multi-modal sensing suite integration
• Learning-based navigation policies implementation