Semantic-level Decentralized Multi-Robot Decision-Making using Probabilistic Macro-Observations
Authors:
- Shayegan OmidshafieiSOShayegan Omidshafiei
- Shih-Yuan LiuSLShih-Yuan Liu
- Michael EverettMEMichael Everett
- Brett T. LopezBLBrett T. Lopez
- Christopher AmatoCAChristopher Amato
- Miao LiuMLMiao Liu
- Jonathan P. HowJHJonathan P. How
- John VianJVJohn Vian
Preprint
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.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- A Concise Introduction to Decentralized POMDPs2016
- MAR-CPS: Measurable Augmented Reality for Prototyping Cyber-Physical Systems2015
- Multi-camera object detection for robotics2010
- Policy Iteration for Decentralized Control of Markov Decision ProcessesJournal of Artificial Intelligence Research, 2009
- Robot task planning using semantic mapsRobotics and Autonomous Systems, 2008
- The Complexity of Decentralized Control of Markov Decision ProcessesMathematics of Operations Research, 2002
- Methods of combining multiple classifiers and their applications to handwriting recognitionIEEE Transactions on Systems, Man, and Cybernetics, 1992
- Some history of the hierarchical Bayesian methodologyTrabajos de estadistica y de investigacion operativa, 1980
- ImageNet Large Scale Visual Recognition Challenge