1 code implementation • 28 Mar 2024 • Akshay Gopalkrishnan, Ross Greer, Mohan Trivedi
Vision-Language Models (VLMs) and Multi-Modal Language models (MMLMs) have become prominent in autonomous driving research, as these models can provide interpretable textual reasoning and responses for end-to-end autonomous driving safety tasks using traffic scene images and other data modalities.
no code implementations • 14 Sep 2023 • Ross Greer, Akshay Gopalkrishnan, Sumega Mandadi, Pujitha Gunaratne, Mohan M. Trivedi, Thomas D. Marcotte
About 30% of all traffic crash fatalities in the United States involve drunk drivers, making the prevention of drunk driving paramount to vehicle safety in the US and other locations which have a high prevalence of driving while under the influence of alcohol.
no code implementations • 27 Jul 2023 • Akshay Gopalkrishnan, Ross Greer, Maitrayee Keskar, Mohan Trivedi
Vehicle light detection, association, and localization are required for important downstream safe autonomous driving tasks, such as predicting a vehicle's light state to determine if the vehicle is making a lane change or turning.
no code implementations • 26 Jul 2023 • Ross Greer, Akshay Gopalkrishnan, Maitrayee Keskar, Mohan Trivedi
Overall, this paper provides insights into the representation of vehicle lights and the importance of accurate annotations for training effective detection models in autonomous driving applications.
no code implementations • 8 May 2023 • Ross Greer, Akshay Gopalkrishnan, Jacob Landgren, Lulua Rakla, Anish Gopalan, Mohan Trivedi
One of the most important tasks for ensuring safe autonomous driving systems is accurately detecting road traffic lights and accurately determining how they impact the driver's actions.
1 code implementation • 8 May 2023 • Ross Greer, Samveed Desai, Lulua Rakla, Akshay Gopalkrishnan, Afnan Alofi, Mohan Trivedi
It is critical for vehicles to prevent any collisions with pedestrians.
no code implementations • 14 Jan 2023 • Ross Greer, Lulua Rakla, Samveed Desai, Afnan Alofi, Akshay Gopalkrishnan, Mohan Trivedi
Moreover, we use the number of correct advisories, false advisories, and missed advisories to define precision and recall performance metrics to evaluate CHAMP.
no code implementations • 14 Jan 2023 • Ross Greer, Akshay Gopalkrishnan, Nachiket Deo, Akshay Rangesh, Mohan Trivedi
Next, we use a custom salience loss function, Salience-Sensitive Focal Loss, to train a Deformable DETR object detection model in order to emphasize stronger performance on salient signs.