Adaptive Meta-Learning for Identification of Rover-Terrain Dynamics
This addresses safety and efficiency issues for autonomous rovers in varying terrain conditions, but it is incremental as it builds on existing meta-learning and Bayesian methods.
The paper tackles the problem of rovers getting stuck in unexpected terrain by using a meta-learning approach to adapt probabilistic predictions of rover-terrain dynamics, resulting in interpretable estimates of terrain parameters.
Rovers require knowledge of terrain to plan trajectories that maximize safety and efficiency. Terrain type classification relies on input from human operators or machine learning-based image classification algorithms. However, high level terrain classification is typically not sufficient to prevent incidents such as rovers becoming unexpectedly stuck in a sand trap; in these situations, online rover-terrain interaction data can be leveraged to accurately predict future dynamics and prevent further damage to the rover. This paper presents a meta-learning-based approach to adapt probabilistic predictions of rover dynamics by augmenting a nominal model affine in parameters with a Bayesian regression algorithm (P-ALPaCA). A regularization scheme is introduced to encourage orthogonality of nominal and learned features, leading to interpretable probabilistic estimates of terrain parameters in varying terrain conditions.