Semantically-enhanced Deep Collision Prediction for Autonomous Navigation using Aerial Robots

被引:2
|
作者
Kulkarni, Mihir [1 ]
Nguyen, Huan [1 ]
Alexis, Kostas [1 ]
机构
[1] Norwegian Univ Sci & Technol NTNU, Autonomous Robots Lab, OS Bragstads Plass 2D, N-7034 Trondheim, Norway
关键词
MOTION;
D O I
10.1109/IROS55552.2023.10342297
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
This paper contributes a novel and modularized learning-based method for aerial robots navigating cluttered environments containing hard-to-perceive thin obstacles without assuming access to a map or the full pose estimation of the robot. The proposed solution builds upon a semantically-enhanced Variational Autoencoder that is trained with both real-world and simulated depth images to compress the input data, while preserving semantically-labeled thin obstacles and handling invalid pixels in the depth sensor's output. This compressed representation, in addition to the robot's partial state involving its linear/angular velocities and its attitude are then utilized to train an uncertainty-aware 3D Collision Prediction Network in simulation to predict collision scores for candidate action sequences in a predefined motion primitives library. A set of simulation and experimental studies in cluttered environments with various sizes and types of obstacles, including multiple hard-to-perceive thin objects, were conducted to evaluate the performance of the proposed method and compare against an end-to-end trained baseline. The results demonstrate the benefits of the proposed semantically-enhanced deep collision prediction for learning-based autonomous navigation.
引用
收藏
页码:3056 / 3063
页数:8
相关论文
共 50 条
  • [31] Autonomous mobile robots navigation using RBF neural compensator
    Rossomando, Francisco G.
    Soria, Carlos
    Carelli, Ricardo
    CONTROL ENGINEERING PRACTICE, 2011, 19 (03) : 215 - 222
  • [32] Artificial pheromone system using RFID for navigation of autonomous robots
    Herianto
    Sakakibara, Toshiki
    Kurabayashi, Daisuke
    JOURNAL OF BIONIC ENGINEERING, 2007, 4 (04) : 245 - 253
  • [33] Artificial Pheromone System Using RFID for Navigation of Autonomous Robots
    Herianto
    Toshiki Sakakibara
    Daisuke Kurabayashi
    Journal of Bionic Engineering, 2007, (04) : 245 - 253
  • [34] Navigation of autonomous robots using fuzzy-neural networks
    Markusek, J
    Vitko, A
    Jurisica, L
    PROCEEDINGS OF THE 2ND INTERNATIONAL CONFERENCE ON CLIMBING AND WALKING ROBOTS, CLAWAR 99, 1999, : 123 - 131
  • [35] Navigation of autonomous robots using a genetic-fuzzy approach
    Department of Computer Science, Coastal Carolina University, Conway, SC, United States
    WSEAS Trans. Syst., 2006, 2 (353-359):
  • [36] Deep Imitation Learning for Safe Indoor Autonomous Micro Aerial Vehicle Navigation
    Candare, Rudolph Joshua
    Daguil, Rolyn C.
    2020 IEEE 12TH INTERNATIONAL CONFERENCE ON HUMANOID, NANOTECHNOLOGY, INFORMATION TECHNOLOGY, COMMUNICATION AND CONTROL, ENVIRONMENT, AND MANAGEMENT (HNICEM), 2020,
  • [37] Assisted Physical Interaction: Autonomous Aerial Robots with Neural Network Detection, Navigation, and Safety Layers
    Berra, Andrea
    Sankaranarayanan, Viswa Narayanan
    Seisa, Achilleas Santi
    Mellet, Julien
    Gamage, Udayanga G. W. K. N.
    Satpute, Sumeet Gajanan
    Ruggiero, Fabio
    Lippiello, Vincenzo
    Tolu, Silvia
    Fumagalli, Matteo
    Nikolakopoulos, George
    Soto, Miguel Angel Trujillo
    Heredia, Guillermo
    2024 INTERNATIONAL CONFERENCE ON UNMANNED AIRCRAFT SYSTEMS, ICUAS, 2024, : 1354 - 1361
  • [38] Incremental Learning for Autonomous Navigation of Mobile Robots based on Deep Reinforcement Learning
    Manh Luong
    Cuong Pham
    Journal of Intelligent & Robotic Systems, 2021, 101
  • [39] Autonomous navigation and collision prediction of port channel based on computer vision and lidar
    Zhang, Zhan
    Yang, Nanwu
    Yang, Yijian
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [40] Incremental Learning for Autonomous Navigation of Mobile Robots based on Deep Reinforcement Learning
    Manh Luong
    Cuong Pham
    JOURNAL OF INTELLIGENT & ROBOTIC SYSTEMS, 2021, 101 (01)