Approximate Bayesian Inference in Spatial Environments

Citations Over TimeTop 11% of 2019 papers

Abstract

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.

Related Papers

• → Batman: Bayesian Target Modelling For Active Inference(2020)2 cited
• → Bayesian incremental inference update by re-using calculations from belief space planning: a new paradigm(2022)1 cited
• Exploration of Hume's Problem(2014)
• → Bayesian Incremental Inference Update by Re-using Calculations from\n Belief Space Planning: A New Paradigm(2019)