Autonomous Navigation in Unknown Environments with Sparse Bayesian Kernel-based Occupancy Mapping

This paper focuses on online occupancy mapping and real-time collision checking onboard an autonomous robot navigating in a large unknown environment. Commonly used voxel and octree map representations can be easily maintained in a small environment but have increasing memory requirements as the environment grows. We propose a fundamentally different approach for occupancy mapping, in which the boundary between occupied and free space is viewed as the decision boundary of a machine learning classifier. This work generalizes a kernel perceptron model which maintains a very sparse set of support vectors to represent the environment boundaries efficiently. We develop a probabilistic formulation based on Relevance Vector Machines, allowing robustness to measurement noise and localization errors as well as probabilistic occupancy classification, supporting autonomous navigation. We provide an online training algorithm, updating the sparse Bayesian map incrementally from streaming range data, and an efficient collision-checking method for general curves, representing potential robot trajectories. The effectiveness of our mapping and collision checking algorithms is evaluated in tasks requiring autonomous robot navigation in unknown environments.

[1]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[2]  Daniel E. Koditschek,et al.  Exact robot navigation using power diagrams , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[3]  Emilio Frazzoli,et al.  Incremental Sampling-based Algorithms for Optimal Motion Planning , 2010, Robotics: Science and Systems.

[4]  Stefan Leutenegger,et al.  ElasticFusion: Real-time dense SLAM and light source estimation , 2016, Int. J. Robotics Res..

[5]  Wolfram Burgard,et al.  OctoMap: an efficient probabilistic 3D mapping framework based on octrees , 2013, Autonomous Robots.

[6]  Mo Shan,et al.  OrcVIO: Object residual constrained Visual-Inertial Odometry , 2020, ArXiv.

[7]  Dinesh Manocha,et al.  FCL: A general purpose library for collision and proximity queries , 2012, 2012 IEEE International Conference on Robotics and Automation.

[8]  Pan,et al.  Efficient Configuration Space Construction ant Dptimization for Motion Planning , 2015 .

[9]  Luca Carlone,et al.  Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[10]  Davide Scaramuzza,et al.  Voxel Map for Visual SLAM , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Avideh Zakhor,et al.  AtomMap: A probabilistic amorphous 3D map representation for robotics and surface reconstruction , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[12]  Shaojie Shen,et al.  Improving octree-based occupancy maps using environment sparsity with application to aerial robot navigation , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Michael M. Kazhdan,et al.  Poisson surface reconstruction , 2006, SGP '06.

[14]  Marc Levoy,et al.  A volumetric method for building complex models from range images , 1996, SIGGRAPH.

[15]  Luca Maria Gambardella,et al.  Human-friendly robot navigation in dynamic environments , 2013, 2013 IEEE International Conference on Robotics and Automation.

[16]  Sven Koenig,et al.  Sensor-based planning with the freespace assumption , 1997, Proceedings of International Conference on Robotics and Automation.

[17]  Jaime Valls Miró,et al.  Warped Gaussian Processes Occupancy Mapping With Uncertain Inputs , 2017, IEEE Robotics and Automation Letters.

[18]  Matteo Matteucci,et al.  Real-Time CPU-Based Large-Scale Three-Dimensional Mesh Reconstruction , 2018, IEEE Robotics and Automation Letters.

[19]  Emmanouil Tsardoulias,et al.  A Review of Global Path Planning Methods for Occupancy Grid Maps Regardless of Obstacle Density , 2016, J. Intell. Robotic Syst..

[20]  Emilio Frazzoli,et al.  Efficient collision checking in sampling-based motion planning via safety certificates , 2016, Int. J. Robotics Res..

[21]  Alberto Elfes,et al.  Using occupancy grids for mobile robot perception and navigation , 1989, Computer.

[22]  Kris K. Hauser,et al.  An empirical study of optimal motion planning , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[23]  Daniel D. Lee,et al.  Learning high-dimensional Mixture Models for fast collision detection in Rapidly-Exploring Random Trees , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[24]  George Eastman House,et al.  Sparse Bayesian Learning and the Relevan e Ve tor Ma hine , 2001 .

[25]  Ming Zeng,et al.  Octree-based fusion for realtime 3D reconstruction , 2013, Graph. Model..

[26]  Michael E. Tipping The Relevance Vector Machine , 1999, NIPS.

[27]  Marco Pavone,et al.  Safe Motion Planning in Unknown Environments: Optimality Benchmarks and Tractable Policies , 2018, Robotics: Science and Systems.

[28]  David J. C. MacKay,et al.  The Evidence Framework Applied to Classification Networks , 1992, Neural Computation.

[29]  Sean L. Bowman,et al.  Probabilistic data association for semantic SLAM , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[30]  Michael C. Yip,et al.  Autonomous Navigation in Unknown Environments using Sparse Kernel-based Occupancy Mapping , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[31]  Shichao Yang,et al.  CubeSLAM: Monocular 3-D Object SLAM , 2018, IEEE Transactions on Robotics.

[32]  Fabio Tozeto Ramos,et al.  Bayesian Hilbert Maps for Dynamic Continuous Occupancy Mapping , 2017, CoRL.

[33]  Olaf Kähler,et al.  Real-Time Large-Scale Dense 3D Reconstruction with Loop Closure , 2016, ECCV.

[34]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[35]  Margarita Chli,et al.  Real-time mesh-based scene estimation for aerial inspection , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[36]  Chao Yang,et al.  ARPACK users' guide - solution of large-scale eigenvalue problems with implicitly restarted Arnoldi methods , 1998, Software, environments, tools.

[37]  Michael E. Tipping,et al.  Fast Marginal Likelihood Maximisation for Sparse Bayesian Models , 2003 .

[38]  Michael Kaess,et al.  Simultaneous localization and mapping with infinite planes , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[39]  Matthias Nießner,et al.  Real-time 3D reconstruction at scale using voxel hashing , 2013, ACM Trans. Graph..

[40]  Stefan Leutenegger,et al.  Efficient Octree-Based Volumetric SLAM Supporting Signed-Distance and Occupancy Mapping , 2018, IEEE Robotics and Automation Letters.

[41]  Wolfram Burgard,et al.  Improved Techniques for Grid Mapping With Rao-Blackwellized Particle Filters , 2007, IEEE Transactions on Robotics.

[42]  Dieter Fox,et al.  RGB-D mapping: Using Kinect-style depth cameras for dense 3D modeling of indoor environments , 2012, Int. J. Robotics Res..

[43]  Michael C. Yip,et al.  Learning-Based Proxy Collision Detection for Robot Motion Planning Applications , 2019, IEEE Transactions on Robotics.

[44]  Andrew W. Fitzgibbon,et al.  KinectFusion: real-time 3D reconstruction and interaction using a moving depth camera , 2011, UIST.

[45]  Fabio Tozeto Ramos,et al.  Hilbert maps: Scalable continuous occupancy mapping with stochastic gradient descent , 2015, Robotics: Science and Systems.

[46]  Brendan Englot,et al.  Fast, accurate gaussian process occupancy maps via test-data octrees and nested Bayesian fusion , 2016, 2016 IEEE International Conference on Robotics and Automation (ICRA).

[47]  Ian T. Nabney,et al.  Efficient Training Of Rbf Networks For Classification , 2004, Int. J. Neural Syst..

[48]  Michael C. Yip,et al.  Fastron: An Online Learning-Based Model and Active Learning Strategy for Proxy Collision Detection , 2017, CoRL.

[49]  Siddhartha S. Srinivasa,et al.  Chisel: Real Time Large Scale 3D Reconstruction Onboard a Mobile Device using Spatially Hashed Signed Distance Fields , 2015, Robotics: Science and Systems.

[50]  Michael Milford,et al.  QuadricSLAM: Dual Quadrics From Object Detections as Landmarks in Object-Oriented SLAM , 2018, IEEE Robotics and Automation Letters.

[51]  Kartik Mohta,et al.  Search-based motion planning for quadrotors using linear quadratic minimum time control , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[52]  Roland Siegwart,et al.  Voxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning , 2016, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[53]  Alessandro De Luca,et al.  Stabilization of the Unicycle Via Dynamic Feedback Linearization , 2000 .

[54]  Cyrill Stachniss,et al.  Efficient Surfel-Based SLAM using 3D Laser Range Data in Urban Environments , 2018, Robotics: Science and Systems.

[55]  Kris Hauser,et al.  Lazy collision checking in asymptotically-optimal motion planning , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[56]  Fabio Tozeto Ramos,et al.  Gaussian process occupancy maps* , 2012, Int. J. Robotics Res..

[57]  Jaume Franch,et al.  Control and trajectory generation of an Ackerman vehicle by dynamic linearization , 2009, 2009 European Control Conference (ECC).

[58]  Sebastian Thrun,et al.  Probabilistic robotics , 2002, CACM.

[59]  Shaojie Shen,et al.  Real-time Scalable Dense Surfel Mapping , 2019, 2019 International Conference on Robotics and Automation (ICRA).

[60]  Jonathan P. How,et al.  Aggressive 3-D collision avoidance for high-speed navigation , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).