A Hough transform approach to safety-aware scalar field mapping using Gaussian Processes
Muzaffar Qureshi, Trivikram Satharasi, Tochukwu E. Ogri, Kyle Volle, Rushikesh Kamalapurkar
TLDR
This paper introduces a Gaussian Process and Hough transform framework for robots to safely map scalar fields while avoiding high-intensity unsafe regions.
Key contributions
- Models scalar fields using Gaussian Processes for Bayesian inference and uncertainty quantification.
- Estimates high-intensity unsafe regions in real-time with Hough transform, leveraging GP posterior.
- Employs a safe sampling strategy with probabilistic guarantees to guide robot away from danger.
- Facilitates safe motion planning by identifying and avoiding hazardous high-intensity areas.
Why it matters
This research provides a robust framework for autonomous robots to map environments safely, crucial for applications in hazardous settings. By integrating GP and Hough transform, it enables real-time hazard identification and avoidance, improving both efficiency and safety during exploration.
Original Abstract
This paper presents a framework for mapping unknown scalar fields using a sensor-equipped autonomous robot operating in unsafe environments. The unsafe regions are defined as regions of high-intensity, where the field value exceeds a predefined safety threshold. For safe and efficient mapping of the scalar field, the sensor-equipped robot must avoid high-intensity regions during the measurement process. In this paper, the scalar field is modeled as a sample from a Gaussian process (GP), which enables Bayesian inference and provides closed-form expressions for both the predictive mean and the uncertainty. Concurrently, the spatial structure of the high-intensity regions is estimated in real-time using the Hough transform (HT), leveraging the evolving GP posterior. A safe sampling strategy is then employed to guide the robot towards safe measurement locations, using probabilistic safety guarantees on the evolving GP posterior. The estimated high-intensity regions also facilitate the design of safe motion plans for the robot. The effectiveness of the approach is verified through two numerical simulation studies and an indoor experiment for mapping a light-intensity field using a wheeled mobile robot.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.