Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Alliance Grants

University of Toronto

$117,000.00

Following Safe Paths from Demonstration in Unmapped Environments

EF 2024-25

Résumé
Autonomous driving technologies continue to advance steadily due to the immense investment around the world in the development of robust perception, planning and control system for self-driving vehicles. However, adverse weather conditions remain a signficant challenge for many autonomy solutions, as they can lead to significant changes in vehicle behaviour, available tire forces and sensor degradation. This project seeks to target two specific challenges in the winter autonomous driving domain, namely identification of drivable paths on snow-covered roadways, and leader following techniques to guide autonomous vehicles when sensor data is diminished. The research team will develop automated labelling techniques by traversing repeated routes in wide-ranging snowy weather for degraded lane and tire track path detection, and will devise methods to infer safe driving paths from the actions of other agents on the road. We will also build online mapping based leader following control methods based on our successful Visual Teach and Repeat paradigm, wherein a lead vehicle will map a local winter scene and communicate only the essential information needed to follow it reliably to trailing vehicles. These approaches will greatly accelerate the adoption of autonomous driving technology in Northern climates, by enabling safe operations in severe winter storms, and will eliminate the reliance on detailed HD maps when weather conditions require abnormal driving behaviours. In working with GM as our partners, we anticipate rapid and widespread deployment of these novel technologies in existing and upcoming advanced driver assistance products.
Programme
Alliance Grants
Bénéficiaire
Emplacement
Ontario, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
590982-2023
Name nom
Waslander, Steven SHL
Department département
Aerospace Studies, Institute for
Organization id
31
Institution établissement
University of Toronto
Province en
Ontario
Province fr
Ontario
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2023
Award amount
117000
Program id
ALLRP
Program name en
Alliance Grants
Program name fr
Subventions Alliance
Group en
RESEARCH PARTNERSHIPS
Group fr
PARTENARIATS DE RECHERCHE
Committee code
96
Committee name en
RPP Internal Decision Cttee
Committee name fr
Cté de décision interne - PPR
Area of application code
700
Area of application group en
Transportation systems and services
Area of application group fr
Services et systèmes de transport
Area of application en
Transportation systems and services
Area of application fr
Services et systèmes de transport
Research subject code
2600
Research subject group en
Robotics
Research subject group fr
Robotique
Research subject en
Robotics
Research subject fr
Robotique
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Following Safe Paths from Demonstration in Unmapped Environments
Keywords
artificial intelligence; autonomous vehicles; perception; robotics; vehicle control; winter
Application summary
Autonomous driving technologies continue to advance steadily due to the immense investment around the world in the development of robust perception, planning and control system for self-driving vehicles. However, adverse weather conditions remain a signficant challenge for many autonomy solutions, as they can lead to significant changes in vehicle behaviour, available tire forces and sensor degradation. This project seeks to target two specific challenges in the winter autonomous driving domain, namely identification of drivable paths on snow-covered roadways, and leader following techniques to guide autonomous vehicles when sensor data is diminished. The research team will develop automated labelling techniques by traversing repeated routes in wide-ranging snowy weather for degraded lane and tire track path detection, and will devise methods to infer safe driving paths from the actions of other agents on the road. We will also build online mapping based leader following control methods based on our successful Visual Teach and Repeat paradigm, wherein a lead vehicle will map a local winter scene and communicate only the essential information needed to follow it reliably to trailing vehicles. These approaches will greatly accelerate the adoption of autonomous driving technology in Northern climates, by enabling safe operations in severe winter storms, and will eliminate the reliance on detailed HD maps when weather conditions require abnormal driving behaviours. In working with GM as our partners, we anticipate rapid and widespread deployment of these novel technologies in existing and upcoming advanced driver assistance products.