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

03/16/2017
by   Shayegan Omidshafiei, et al.
0

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.

READ FULL TEXT

page 1

page 7

page 8

research
02/20/2015

Decentralized Control of Partially Observable Markov Decision Processes using Belief Space Macro-actions

The focus of this paper is on solving multi-robot planning problems in c...
research
07/24/2017

Learning for Multi-robot Cooperation in Partially Observable Stochastic Environments with Macro-actions

This paper presents a data-driven approach for multi-robot coordination ...
research
09/20/2022

Macro-Action-Based Multi-Agent/Robot Deep Reinforcement Learning under Partial Observability

The state-of-the-art multi-agent reinforcement learning (MARL) methods h...
research
02/12/2014

Planning for Decentralized Control of Multiple Robots Under Uncertainty

We describe a probabilistic framework for synthesizing control policies ...
research
02/16/2018

An Anytime Algorithm for Task and Motion MDPs

Integrated task and motion planning has emerged as a challenging problem...
research
03/01/2022

T^3OMVP: A Transformer-based Time and Team Reinforcement Learning Scheme for Observation-constrained Multi-Vehicle Pursuit in Urban Area

Smart Internet of Vehicles (IoVs) combined with Artificial Intelligence ...
research
12/28/2017

Multi-Modal Active Perception for Information Gathering in Science Missions

Robotic science missions in remote environments, such as deep ocean and ...

Please sign up or login with your details

Forgot password? Click here to reset