An Active Perception Game for Robust Information Gathering

2024-03-31

AI Summary

In critical scenarios such as trapped-person localization, conventional active perception suffers from suboptimal viewpoint selection and high decision risk due to biased information gain estimation. To address this, this paper pioneers a game-theoretic formulation of active perception, introducing a novel online method to estimate the discrepancy between true and expected information gain—achieving sublinear regret convergence. Integrating information theory, game theory, and online learning, our framework supports multimodal sensing, heterogeneous map representations, and deployment on both simulation and real-world platforms (quadrotors and Jackal robots). Experiments demonstrate a 42% average reduction in information gain estimation error, a 7% increase in actual information collected, a 5 dB improvement in image reconstruction PSNR, a 6% gain in semantic localization accuracy, and effective robot-driven exploration of occluded regions.

Technology Category

• Machine Learning: Active Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Search and Optimization: Learning to Search

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Active perception approaches select future viewpoints by using some estimate of the information gain. An inaccurate estimate can be detrimental in critical situations, e.g., locating a person in distress. However the true information gained can only be calculated post hoc, i.e., after the observation is realized. We present an approach to estimate the discrepancy between the estimated information gain (which is the expectation over putative future observations while neglecting correlations among them) and the true information gain. The key idea is to analyze the mathematical relationship between active perception and the estimation error of the information gain in a game-theoretic setting. Using this, we develop an online estimation approach that achieves sub-linear regret (in the number of time-steps) for the estimation of the true information gain and reduces the sub-optimality of active perception systems. We demonstrate our approach for active perception using a comprehensive set of experiments on: (a) different types of environments, including a quadrotor in a photorealistic simulation, real-world robotic data, and real-world experiments with ground robots exploring indoor and outdoor scenes; (b) different types of robotic perception data; and (c) different map representations. On average, our approach reduces information gain estimation errors by 42%, increases the information gain by 7%, PSNR by 5%, and semantic accuracy (measured as the number of objects that are localized correctly) by 6%. In real-world experiments with a Jackal ground robot, our approach demonstrated complex trajectories to explore occluded regions.

Problem

• Estimates discrepancy between expected and true information gain.
• Reduces sub-optimality in active perception systems.
• Improves accuracy in locating objects in various environments.

Innovation

• Game-theoretic analysis of information gain discrepancy
• Online estimation with sub-linear regret performance
• Reduces estimation errors and improves perception accuracy