A Contextual Bandit Approach for Learning to Plan in Environments with Probabilistic Goal Configurations
This work addresses the problem of navigating to movable objects for robotics and embodied AI, representing an incremental improvement over methods limited to static objects.
The paper tackles object-goal navigation by developing a modular framework that efficiently searches for both static and movable objects in indoor environments, using a contextual-bandit agent and weighted minimum latency solver, achieving high sample efficiency and reliability in simulated and real-world evaluations.
Object-goal navigation (Object-nav) entails searching, recognizing and navigating to a target object. Object-nav has been extensively studied by the Embodied-AI community, but most solutions are often restricted to considering static objects (e.g., television, fridge, etc.). We propose a modular framework for object-nav that is able to efficiently search indoor environments for not just static objects but also movable objects (e.g. fruits, glasses, phones, etc.) that frequently change their positions due to human intervention. Our contextual-bandit agent efficiently explores the environment by showing optimism in the face of uncertainty and learns a model of the likelihood of spotting different objects from each navigable location. The likelihoods are used as rewards in a weighted minimum latency solver to deduce a trajectory for the robot. We evaluate our algorithms in two simulated environments and a real-world setting, to demonstrate high sample efficiency and reliability.