Efficient Online Learning and Adaptive Planning for Robotic Information Gathering Based on Streaming Data

2025-07-17

AI Summary

For robotic scalar field mapping in unknown or time-varying environments, existing Gaussian process (GP) methods suffer from low online learning efficiency and poor real-time performance on large-scale data. This paper proposes a streaming sparse Gaussian process (FS-GP) framework that integrates incremental sparse approximation, online hyperparameter adaptation, and information-driven adaptive path planning. The approach reduces computational complexity from $O(n^3)$ to $O(m^2 n)$, where $m ll n$. Evaluated on both synthetic and real-world datasets, FS-GP achieves mapping accuracy comparable to full GP baselines while accelerating inference by one to two orders of magnitude and reducing memory consumption by over 60%. These improvements significantly enhance scalability and real-time responsiveness for long-term autonomous exploration.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Data management and stream processing for Web, mobile and wireless applications

Abstract

Robotic information gathering (RIG) techniques refer to methods where mobile robots are used to acquire data about the physical environment with a suite of sensors. Informative planning is an important part of RIG where the goal is to find sequences of actions or paths that maximize efficiency or the quality of information collected. Many existing solutions solve this problem by assuming that the environment is known in advance. However, real environments could be unknown or time-varying, and adaptive informative planning remains an active area of research. Adaptive planning and incremental online mapping are required for mapping initially unknown or varying spatial fields. Gaussian process (GP) regression is a widely used technique in RIG for mapping continuous spatial fields. However, it falls short in many applications as its real-time performance does not scale well to large datasets. To address these challenges, this paper proposes an efficient adaptive informative planning approach for mapping continuous scalar fields with GPs with streaming sparse GPs. Simulation experiments are performed with a synthetic dataset and compared against existing benchmarks. Finally, it is also verified with a real-world dataset to further validate the efficacy of the proposed method. Results show that our method achieves similar mapping accuracy to the baselines while reducing computational complexity for longer missions.

Problem

• Adaptive planning for unknown or time-varying environments
• Efficient online learning with streaming sparse GPs
• Reducing computational complexity in robotic information gathering

Innovation

• Uses streaming sparse GPs for efficiency
• Adapts planning for unknown environments
• Reduces computational complexity significantly