Approximate Bayesian Inference in Spatial Environments
Atanas Mirchev, Baris Kayalibay, Maximilian Soelch, Patrick van der Smagt, Justin Bayer · 2019
Model-based approaches bear great promise for decision making of agents interacting with the physical world.In the context of spatial environments, different types of problems such as localisation, mapping, navigation or autonomous exploration are typically adressed with specialised methods, often relying on detailed knowledge of the system at hand.We express these tasks as probabilistic inference and planning under the umbrella of deep sequential generative models.Using the frameworks of variational inference and neural networks, our method inherits favourable properties such as flexibility, scalability and the ability to learn from data.The method performs comparably to specialised stateof-the-art methodology in two distinct simulated environments.