AquaVis: A Perception-Aware Autonomous Navigation Framework for Underwater Vehicles

Visual monitoring operations underwater require both observing the objects of interest in close-proximity, and tracking the few feature-rich areas necessary for state estimation. This paper introduces the first navigation framework, called AquaVis, that produces on-line visibility-aware motion plans that enable Autonomous Underwater Vehicles (AUVs) to track multiple visual objectives with an arbitrary camera configuration in real-time. Using the proposed pipeline, AUVs can efficiently move in 3D, reach their goals while avoiding obstacles safely, and maximizing the visibility of multiple objectives along the path within a specified proximity. The method is sufficiently fast to be executed in real-time and is suitable for single or multiple camera configurations. Experimental results show the significant improvement on tracking multiple automatically-extracted points of interest, with low computational overhead and fast re-planning times.Accompanying short video: https://youtu.be/JKO bbrIZyU

[1]  Ioannis M. Rekleitis.  Multi-robot simultaneous localization and uncertainty reduction on maps (MR-SLURM) , 2013, 2013 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[2]  Wolfram Burgard,et al.  Exploration with active loop-closing for FastSLAM , 2004, 2004 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (IEEE Cat. No.04CH37566).

[3]  Alberto Quattrini Li,et al.  Sonar Visual Inertial SLAM of Underwater Structures , 2018, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Ryan M. Eustice,et al.  Opportunistic sampling-based active visual SLAM for underwater inspection , 2016, Auton. Robots.

[5]  François Chaumette,et al.  Vision-based minimum-time trajectory generation for a quadrotor UAV , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[6]  Florian Shkurti,et al.  Vision-Based Goal-Conditioned Policies for Underwater Navigation in the Presence of Obstacles , 2020, RSS 2020.

[7]  Marin Kobilarov,et al.  Optimal Visual Servoing for differentially flat underactuated systems , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[8]  Davide Scaramuzza,et al.  Fisher Information Field: an Efficient and Differentiable Map for Perception-aware Planning , 2020, ArXiv.

[9]  Daniele Nardi,et al.  Effective target aware visual navigation for UAVs , 2017, 2017 European Conference on Mobile Robots (ECMR).

[10]  Sertac Karaman,et al.  Perception-aware time optimal path parameterization for quadrotors , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[11]  Gregory Dudek,et al.  Vision-Based Autonomous Underwater Swimming in Dense Coral for Combined Collision Avoidance and Target Selection , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[12]  Rafael Murrieta-Cid,et al.  Maintaining Visibility of a Landmark using Optimal Sampling-based Path Planning , 2019, Computación y Sistemas.

[13]  Davide Scaramuzza,et al.  Appearance-based Active, Monocular, Dense Reconstruction for Micro Aerial Vehicles , 2014, Robotics: Science and Systems.

[14]  Paolo Valigi,et al.  Exploiting Photometric Information for Planning Under Uncertainty , 2015, ISRR.

[15]  Lingjie Yang,et al.  An Optimized Image-Based Visual Servo Control for Fixed-Wing Unmanned Aerial Vehicle Target Tracking With Fixed Camera , 2019, IEEE Access.

[16]  Alexei Makarenko,et al.  An experiment in integrated exploration , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Jason M. O'Kane,et al.  Experimental Comparison of Open Source Vision-Based State Estimation Algorithms , 2016, ISER.

[18]  Gregory Dudek,et al.  Uncertainty Reduction via Heuristic Search Planning on Hybrid Metric/Topological Map , 2015, 2015 12th Conference on Computer and Robot Vision.

[19]  Andrew Hogue,et al.  AQUA: An Amphibious Autonomous Robot , 2007, Computer.

[20]  Frank Dellaert,et al.  Planning in the continuous domain: A generalized belief space approach for autonomous navigation in unknown environments , 2015, Int. J. Robotics Res..

[21]  David Whitney,et al.  Ear-based exploration on hybrid metric/topological maps , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[22]  Sertac Karaman,et al.  Perception-aware trajectory generation for aggressive quadrotor flight using differential flatness , 2019, 2019 American Control Conference (ACC).

[23]  Daniele Nardi,et al.  Joint Vision-Based Navigation, Control and Obstacle Avoidance for UAVs in Dynamic Environments , 2019, 2019 European Conference on Mobile Robots (ECMR).

[24]  Ioannis M. Rekleitis,et al.  Autonomous 3D Semantic Mapping of Coral Reefs , 2019, FSR.

[25]  Angela P. Schoellig,et al.  A Perception-Aware Flatness-Based Model Predictive Controller for Fast Vision-Based Multirotor Flight , 2020 .

[26]  Pieter Abbeel,et al.  Motion planning with sequential convex optimization and convex collision checking , 2014, Int. J. Robotics Res..

[27]  Alberto Quattrini Li,et al.  SVIn2: An Underwater SLAM System using Sonar, Visual, Inertial, and Depth Sensor , 2018, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[28]  Evangelos A. Theodorou,et al.  Aggressive Perception-Aware Navigation Using Deep Optical Flow Dynamics and PixelMPC , 2020, IEEE Robotics and Automation Letters.

[29]  Alexander Domahidi,et al.  Real-time planning for automated multi-view drone cinematography , 2017, ACM Trans. Graph..

[30]  Hans-Peter Kriegel,et al.  A Density-Based Algorithm for Discovering Clusters in Large Spatial Databases with Noise , 1996, KDD.

[31]  Davide Scaramuzza,et al.  PAMPC: Perception-Aware Model Predictive Control for Quadrotors , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[32]  Junaed Sattar,et al.  Semantically-Aware Strategies for Stereo-Visual Robotic Obstacle Avoidance , 2021, 2021 IEEE International Conference on Robotics and Automation (ICRA).

[33]  John J. Leonard,et al.  Adaptive Mobile Robot Navigation and Mapping , 1999, Int. J. Robotics Res..

[34]  James G. Bellingham,et al.  Can we do better than the grid survey: Optimal synoptic surveys in presence of variable uncertainty and decorrelation scales , 2014 .

[35]  Ioannis M. Rekleitis,et al.  Coverage Path Planning for Mapping of Underwater Structures , 2020, Global Oceans 2020: Singapore – U.S. Gulf Coast.

[36]  Ioannis M. Rekleitis,et al.  Coral Identification and Counting with an Autonomous Underwater Vehicle , 2018, 2018 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[37]  Nando de Freitas,et al.  Active Policy Learning for Robot Planning and Exploration under Uncertainty , 2007, Robotics: Science and Systems.

[38]  François Chaumette,et al.  Coupling active depth estimation and visual servoing via a large projection operator , 2017, Int. J. Robotics Res..

[39]  Alberto Quattrini Li,et al.  MDNet: Multi-Patch Dense Network for Coral Classification , 2018, OCEANS 2018 MTS/IEEE Charleston.

[40]  Alberto Quattrini Li,et al.  Experimental Comparison of Open Source Visual-Inertial-Based State Estimation Algorithms in the Underwater Domain , 2019, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[41]  Ioannis M. Rekleitis.  Simultaneous localization and uncertainty reduction on maps (SLURM): Ear based exploration , 2012, 2012 IEEE International Conference on Robotics and Biomimetics (ROBIO).

[42]  Fei Gao,et al.  RAPTOR: Robust and Perception-Aware Trajectory Replanning for Quadrotor Fast Flight , 2020, IEEE Transactions on Robotics.

[43]  Alberto Quattrini Li,et al.  Underwater cave mapping using stereo vision , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[44]  Jason M. O'Kane,et al.  Navigation in the Presence of Obstacles for an Agile Autonomous Underwater Vehicle , 2020, 2020 IEEE International Conference on Robotics and Automation (ICRA).

[45]  Gregory Dudek,et al.  Feature Tracking Evaluation for Pose Estimation in Underwater Environments , 2011, 2011 Canadian Conference on Computer and Robot Vision.