One Shot Learning Approach to Identify Drivers

This paper presents a new system to steer a powered wheelchair using a Sharp IR sensor and a Raspberry Pi. Interviews with occupational therapists, helpers and carers at Chailey Heritage Foundation/School revealed that clicking noises generated from closing switch contact used to operate powered wheelchairs disturbed the attention and reduced the focus of young wheelchair users having cognitive or physical disability. Also switches often slipped away and became unreachable. The new system replaced lever-switches used to steer powered wheelchairs by an electronic circuit. The circuit consisted of a Sharp IR sensor, Analogue to Digital converter, relays, and a Raspberry Pi. The sharp IR sensor detected movement in its range and the Raspberry Pi interpreted the data and generated commands to steer a powered wheelchair. Two modes were used to overcome the problem of sensors slipping from position: Click to Calibrate and Auto-Calibrate. A technical User Interface was created to modify sensitivity, user and detection settings. Practical testing showed the system behaved satisfactorily. It detected users' voluntary movements and used them to steer a powered wheelchair and overcome the problem of switches slipping from position. Clinical trials will be conducted at Chailey Heritage Foundation.

show abstract

“…Future work will consider creating a new UI to incorporate multiple Users [15,24]. Users could be digitally added to the new system.…”

Section: Discussionmentioning

confidence: 99%

Intelligent User Interface to Control a Powered Wheelchair Using Infrared Sensors

Haddad

Sanders

Tewkesbury

et al. 2021

Lecture Notes in Networks and Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…They have implemented a fully functional system using a camera module, Python language, and a Raspberry Pi. The application of one-shot learning for face recognition has yielded satisfactory results [101]. Additionally, one-shot learning can also be leveraged for surveillance anomaly detection without requiring precise temporal annotations.…”

Section: One Shot Learningmentioning

confidence: 99%

Practical Autonomous Driving: A Survey of Challenges and Opportunities

De,

Saha,

Sallam

et al. 2023

Preprint

View full text Add to dashboard Cite

Autonomous Driving (AD) has become a prominent research area in the field of Artificial Intelligence (AI) and Machine Learning (ML) in recent years. This opens the door wider for self-driving cars to surpass conventional vehicles in the current market share. Despite its apparent simplicity, AD is composed of complex and heterogeneous systems, which are in need of a high level of coordination and alignment to ensure both full automation and safety. Therefore, numerous research studies have been conducted over the last few years to facilitate such coordination and accelerate the capacity of these types of vehicles to be self-managed in complex situations. The paper summarises these approaches that led to building what is known nowadays as the autonomous driving pipeline. Moreover, although skepticism exists regarding the practicality of AD as a viable alternative to traditional vehicles, extensive research suggests the multiple benefits of relying on them for mobility. While challenges remain in implementing AD in the real world, including regulation and technical issues, substantial progress in recent years indicates a growing acceptance of AD in the near future. This paper further explores the advantages and opportunities of the conducted such systems in facilitating the practicality of Autonomous Driving.

show abstract