Active Robot Vision for Distant Object Change Detection: A Lightweight Training Simulator Inspired by Multi-Armed Bandits

TL;DR

This paper introduces a lightweight, simulator-based approach for active robot vision in distant object change detection, utilizing a multi-armed bandit inspired planner to optimize navigation and reduce costs.

Contribution

It presents a novel, efficient simulator requiring only one real-world journey per object, and a hierarchical planner inspired by multi-armed bandits for improved decision-making.

Findings

Simulator accelerates early-stage development and testing.

The hierarchical planner effectively guides robot navigation.

Framework successfully applied to complex scenarios like sofa as bookshelf.

Abstract

In ground-view object change detection, the recently emerging mapless navigation has great potential to navigate a robot to objects distantly detected (e.g., books, cups, clothes) and acquire high-resolution object images, to identify their change states (no-change/appear/disappear). However, naively performing full journeys for every distant object requires huge sense/plan/action costs, proportional to the number of objects and the robot-to-object distance. To address this issue, we explore a new map-based active vision problem in this work: ``Which journey should the robot select next?" However, the feasibility of the active vision framework remains unclear; Since distant objects are only uncertainly recognized, it is unclear whether they can provide sufficient cues for action planning. This work presents an efficient simulator for feasibility testing, to accelerate the early-stage R&D cycles (e.g., prototyping, training, testing, and evaluation). The proposed simulator is designed to identify the degree of difficulty that a robot vision system (sensors/recognizers/planners/actuators) would face when applied to a given environment (workspace/objects). Notably, it requires only one real-world journey experience per distant object to function, making it suitable for an efficient R&D cycle. Another contribution of this work is to present a new lightweight planner inspired by the traditional multi-armed bandit problem. Specifically, we build a lightweight map-based planner on top of the mapless planner, which constitutes a hierarchical action planner. We verified the effectiveness of the proposed framework using a semantically non-trivial scenario ``sofa as bookshelf".