Information-Theoretic Abstractions for Planning in Agents With Computational Constraints

In this paper, we develop a framework for path-planning on abstractions that are not provided to the agent a priori but instead emerge as a function of the available computational resources. We show how a path-planning problem in an environment can be systematically approximated by solving a sequence of easier-to-solve problems on abstractions of the original space. The properties of the problem are analyzed, and a number of theoretical results are presented and discussed. A numerical example is presented to show the utility of the approach and to corroborate the theoretical findings. We conclude by providing a discussion detailing the connections of the proposed approach to anytime algorithms and bounded rationality.

[1]  Naftali Tishby,et al.  The information bottleneck method , 2000, ArXiv.

[2]  Sven Behnke,et al.  Local Multiresolution Path Planning , 2003, RoboCup.

[3]  Thomas M. Cover,et al.  Elements of information theory (2. ed.) , 2006 .

[4]  James M. Rehg,et al.  Multi-scale perception and path planning on probabilistic obstacle maps , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[5]  Panagiotis Tsiotras,et al.  Reduced complexity multi-scale path-planning on probabilistic maps , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[6]  Panagiotis Tsiotras,et al.  Multi-resolution path planning: Theoretical analysis, efficient implementation, and extensions to dynamic environments , 2010, 49th IEEE Conference on Decision and Control (CDC).

[7]  Panagiotis Tsiotras,et al.  Multiresolution Motion Planning for Autonomous Agents via Wavelet-Based Cell Decompositions , 2012, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[8]  Jordi Grau-Moya,et al.  Bounded Rationality, Abstraction, and Hierarchical Decision-Making: An Information-Theoretic Optimality Principle , 2015, Front. Robot. AI.

[9]  P. Tsiotras,et al.  Multiresolution path planning with wavelets: A local replanning approach , 2008, 2008 American Control Conference.

[10]  Mark S. Boddy,et al.  An Analysis of Time-Dependent Planning , 1988, AAAI.

[11]  Panagiotis Tsiotras,et al.  Hierarchical state abstractions for decision-making problems with computational constraints , 2017, 2017 IEEE 56th Annual Conference on Decision and Control (CDC).

[12]  Gerhard K. Kraetzschmar,et al.  Probabilistic quadtrees for variable-resolution mapping of large environments , 2004 .

[13]  Larry S. Davis,et al.  Multiresolution path planning for mobile robots , 1986, IEEE J. Robotics Autom..

[14]  Efstathios Bakolas,et al.  A hierarchical on-line path planning scheme using wavelets , 2007, 2007 European Control Conference (ECC).

[15]  Daniel A. Braun,et al.  Information, Utility and Bounded Rationality , 2011, AGI.

[16]  Panagiotis Tsiotras,et al.  A Beamlet-Based Graph Structure for Path Planning Using Multiscale Information , 2012, IEEE Transactions on Automatic Control.

[17]  Daniel Polani,et al.  Information Theory of Decisions and Actions , 2011 .

[18]  Naftali Tishby,et al.  Agglomerative Information Bottleneck , 1999, NIPS.

[19]  Dimitri P. Bertsekas,et al.  Dynamic Programming and Optimal Control, Two Volume Set , 1995 .

[20]  Raghvendra V. Cowlagi,et al.  Hierarchical motion planning for autonomous aerial and terrestrial vehicles , 2011 .

[21]  Efstathios Bakolas,et al.  Multiresolution Hierarchical Path-Planning for Small UAVs Using Wavelet Decompositions , 2012, J. Intell. Robotic Syst..

[22]  Panagiotis Tsiotras,et al.  Hierarchical Motion Planning with Kinodynamic Feasibility Guarantees , 2011 .

[23]  Naftali Tishby,et al.  Trading Value and Information in MDPs , 2012 .