Choosing the Right Tool for the Job: Online Decision Making Over SLAM Algorithms

Nearly all state-of-the-art SLAM algorithms are designed to exploit patterns in data from specific sensing modal- ities, such as time-of-flight and structured light depth sensors, or RGB cameras. This specialization increases localization accuracy in domains where the given modality detects many high-quality features, but comes at the cost of decreasing perfor- mance in other, less favorable environments. For robotic systems that may experience a wide variety of sensing conditions, this difficulty in generalization presents a significant challenge. In this paper, we propose running several computationally cheap SLAM front ends in parallel and choosing the most promising feature set online. This problem is similar to the Algorithm Selection Problem (ASP), but has several complicating fac- tors that preclude application of existing methods. We first provide an extension of the ASP formalism that captures the unique challenges in the SLAM setting, and then, based on this formalism, we propose modeling the SLAM ASP as a partially observable Markov decision process (POMDP). Our experiments show that dynamically selecting SLAM front ends, even myopically, improves localization robustness compared to selecting a static front end, and that using a POMDP policy provides even greater improvement.