Self-Supervised Sidewalk Perception Using Fast Video Semantic Segmentation for Robotic Wheelchairs in Smart Mobility

Abstract

The real-time segmentation of sidewalk environments is critical to achieving autonomous navigation for robotic wheelchairs in urban territories. A robust and real-time video semantic segmentation offers an apt solution for advanced visual perception in such complex domains. The key to this proposition is to have a method with lightweight flow estimations and reliable feature extractions. We address this by selecting an approach based on recent trends in video segmentation. Although these approaches demonstrate efficient and cost-effective segmentation performance in cross-domain implementations, they require additional procedures to put their striking characteristics into practical use. We use our method for developing a visual perception technique to perform in urban sidewalk environments for the robotic wheelchair. We generate a collection of synthetic scenes in a blending target distribution to train and validate our approach. Experimental results show that our method improves prediction accuracy on our benchmark with tolerable loss of speed and without additional overhead. Overall, our technique serves as a reference to transfer and develop perception algorithms for any cross-domain visual perception applications with less downtime.

DELTA: Integrating Multimodal Sensing with Micromobility for Enhanced Sidewalk and Pedestrian Route Understanding

“…Enhancing Autonomous Navigation with Diverse Sidewalk Segmentation: Autonomous navigation systems have traditionally relied on generic models for sidewalk detection [ 50 ], which may not accurately reflect the diverse characteristics of different urban settings. By integrating customized pathway segmentation with the multi-resolution and diverse sidewalk and pedestrian route detection capabilities of the DELTA dataset, these systems can achieve a much deeper understanding of urban landscapes.…”

A Review on Human-Robot Interaction and User Experience in Smart Robotic Wheelchairs

“…Machine learning and artificial intelligence techniques have enabled adaptive behavior and improved user-machine interaction (Tomari et al, 2012). Sensor fusion and perception algorithms have enhanced the wheelchair's perception capabilities, enabling accurate obstacle detection and environment understanding (Pradeep et al, 2022).…”

Autonomous navigation and obstacle avoidance in smart robotic wheelchairs

“…Traditional manual wheelchairs require constant physical exertion and control from the user, limiting their ability to traverse challenging terrains or navigate crowded spaces. In contrast, smart robotic wheelchairs employ a range of sensors, such as depth cameras, LiDAR (Light Detection and Ranging), and ultrasonic sensors, to perceive the surrounding environment and detect obstacles (Pradeep et al, 2022). This environment perception is further enhanced through the integration of machine learning algorithms and computer vision techniques, enabling the wheelchair to recognize and classify objects and obstacles in real-time.…”