Deep-Learning-Based Context-Aware Multi-Level Information Fusion Systems for Indoor Mobile Robots Safe Navigation
Author:
Jia Yin1, Ramalingam Balakrishnan1ORCID, Mohan Rajesh Elara1ORCID, Yang Zhenyuan1ORCID, Zeng Zimou1, Veerajagadheswar Prabakaran1
Affiliation:
1. Engineering Product Development Pillar, Singapore University of Technology and Design (SUTD), Singapore 487372, Singapore
Abstract
Hazardous object detection (escalators, stairs, glass doors, etc.) and avoidance are critical functional safety modules for autonomous mobile cleaning robots. Conventional object detectors have less accuracy for detecting low-feature hazardous objects and have miss detection, and the false classification ratio is high when the object is under occlusion. Miss detection or false classification of hazardous objects poses an operational safety issue for mobile robots. This work presents a deep-learning-based context-aware multi-level information fusion framework for autonomous mobile cleaning robots to detect and avoid hazardous objects with a higher confidence level, even if the object is under occlusion. First, the image-level-contextual-encoding module was proposed and incorporated with the Faster RCNN ResNet 50 object detector model to improve the low-featured and occluded hazardous object detection in an indoor environment. Further, a safe-distance-estimation function was proposed to avoid hazardous objects. It computes the distance of the hazardous object from the robot’s position and steers the robot into a safer zone using detection results and object depth data. The proposed framework was trained with a custom image dataset using fine-tuning techniques and tested in real-time with an in-house-developed mobile cleaning robot, BELUGA. The experimental results show that the proposed algorithm detected the low-featured and occluded hazardous object with a higher confidence level than the conventional object detector and scored an average detection accuracy of 88.71%.
Funder
National Robotics Programme under its Robotics Enabling Capabilities and Technologies National Robotics Programme under its Robotics Domain Specific Agency for Science, Technology and Research The Singapore University of Technology and Design
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference41 articles.
1. Robots serve humans in public places—KeJia robot as a shopping assistant;Chen;Int. J. Adv. Robot. Syst.,2017 2. Yin, J., Apuroop, K.G.S., Tamilselvam, Y.K., Mohan, R.E., Ramalingam, B., and Le, A.V. (2020). Table cleaning task by human support robot using deep learning technique. Sensors, 20. 3. Pathmakumar, T., Kalimuthu, M., Elara, M.R., and Ramalingam, B. (2021). An autonomous robot-aided auditing scheme for floor cleaning. Sensors, 21. 4. Raj, T., Hanim Hashim, F., Baseri Huddin, A., Ibrahim, M.F., and Hussain, A. (2020). A survey on LiDAR scanning mechanisms. Electronics, 9. 5. An occupancy grid mapping enhanced visual SLAM for real-time locating applications in indoor GPS-denied environments;Xu;Autom. Constr.,2019
|
|