Semantic-level Decentralized Multi-Robot Decision-Making using Probabilistic Macro-Observations

TL;DR

This paper introduces a hierarchical Bayesian macro-observation framework for scalable semantic multi-robot decision-making, demonstrating improved classification accuracy and real-time onboard operation in complex environments.

Contribution

It formalizes macro-observations in Dec-POSMDPs and integrates a hierarchical Bayesian noise inference method into multi-robot planning, enabling real-time semantic decision-making.

Findings

Hierarchical Bayesian Noise Inference outperforms existing methods.

Macro-observation scheme enables scalable semantic decision-making.

First real-time onboard CNN classification on quadrotors in multi-robot domain.

Abstract

Robust environment perception is essential for decision-making on robots operating in complex domains. Intelligent task execution requires principled treatment of uncertainty sources in a robot's observation model. This is important not only for low-level observations (e.g., accelerometer data), but also for high-level observations such as semantic object labels. This paper formalizes the concept of macro-observations in Decentralized Partially Observable Semi-Markov Decision Processes (Dec-POSMDPs), allowing scalable semantic-level multi-robot decision making. A hierarchical Bayesian approach is used to model noise statistics of low-level classifier outputs, while simultaneously allowing sharing of domain noise characteristics between classes. Classification accuracy of the proposed macro-observation scheme, called Hierarchical Bayesian Noise Inference (HBNI), is shown to exceed existing methods. The macro-observation scheme is then integrated into a Dec-POSMDP planner, with hardware experiments running onboard a team of dynamic quadrotors in a challenging domain where noise-agnostic filtering fails. To the best of our knowledge, this is the first demonstration of a real-time, convolutional neural net-based classification framework running fully onboard a team of quadrotors in a multi-robot decision-making domain.