Deep Learning Obstacle Detection and Avoidance for Powered Wheelchair

Tawil, Yahya; Hafez, A. H. Abdul

doi:10.1109/asyu56188.2022.9925493

Cited by 2 publications

(1 citation statement)

References 18 publications

(19 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the scarcity of suitable datasets for wheelchair navigation, researchers often need to collect their samples before conducting training. While promising results have been demonstrated [85,86], the labor-intensive data collection process has impeded widespread adoption. Another approach involves the utilization of recurrent neural networks (RNNs).…”

Section: Related Workmentioning

confidence: 99%

Design of an Assisted Driving System for Obstacle Avoidance Based on Reinforcement Learning Applied to Electrified Wheelchairs

Pacini,

Dini,

Fanucci

2024

Electronics

View full text Add to dashboard Cite

Driving a motorized wheelchair is not without risk and requires high cognitive effort to obtain good environmental perception. Therefore, people with severe disabilities are at risk, potentially lowering their social engagement, and thus, affecting their overall well-being. Therefore, we designed a cooperative driving system for obstacle avoidance based on a trained reinforcement learning (RL) algorithm. The system takes the desired direction and speed from the user via a joystick and the obstacle distribution from a LiDAR placed in front of the wheelchair. Considering both inputs, the system outputs a pair of forward and rotational speeds that ensure obstacle avoidance while being as close as possible to the user commands. We validated it through simulations and compared it with a vector field histogram (VFH). The preliminary results show that the RL algorithm does not disruptively alter the user intention, reduces the number of collisions, and provides better door passages than a VFH; furthermore, it can be integrated on an embedded device. However, it still suffers from higher jerkiness.

show abstract

Section: Related Workmentioning

confidence: 99%

Design of an Assisted Driving System for Obstacle Avoidance Based on Reinforcement Learning Applied to Electrified Wheelchairs

Pacini,

Dini,

Fanucci

2024

Electronics

View full text Add to dashboard Cite

show abstract

State-of-the-Art Review on Wearable Obstacle Detection Systems Developed for Assistive Technologies and Footwear

Joseph

kian

Begg

2023

Sensors

View full text Add to dashboard Cite

Walking independently is essential to maintaining our quality of life but safe locomotion depends on perceiving hazards in the everyday environment. To address this problem, there is an increasing focus on developing assistive technologies that can alert the user to the risk destabilizing foot contact with either the ground or obstacles, leading to a fall. Shoe-mounted sensor systems designed to monitor foot-obstacle interaction are being employed to identify tripping risk and provide corrective feedback. Advances in smart wearable technologies, integrating motion sensors with machine learning algorithms, has led to developments in shoe-mounted obstacle detection. The focus of this review is gait-assisting wearable sensors and hazard detection for pedestrians. This literature represents a research front that is critically important in paving the way towards practical, low-cost, wearable devices that can make walking safer and reduce the increasing financial and human costs of fall injuries.

show abstract

Deep Learning Obstacle Detection and Avoidance for Powered Wheelchair

Cited by 2 publications

References 18 publications

Design of an Assisted Driving System for Obstacle Avoidance Based on Reinforcement Learning Applied to Electrified Wheelchairs

Design of an Assisted Driving System for Obstacle Avoidance Based on Reinforcement Learning Applied to Electrified Wheelchairs

State-of-the-Art Review on Wearable Obstacle Detection Systems Developed for Assistive Technologies and Footwear

Contact Info

Product

Resources

About