no code implementations • 15 May 2024 • Ross Greer, Mohan Trivedi
This study investigates the use of trajectory and dynamic state information for efficient data curation in autonomous driving machine learning tasks.
no code implementations • 23 Apr 2024 • Ross Greer, Mathias Viborg Andersen, Andreas Møgelmose, Mohan Trivedi
In this paper, we present a novel approach leveraging generalizable representations from vision-language models for driver activity classification.
no code implementations • 19 Apr 2024 • Ross Greer, Bjørk Antoniussen, Andreas Møgelmose, Mohan Trivedi
In this paper, we propose VisLED, a language-driven active learning framework for diverse open-set 3D Object Detection.
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 • 29 Feb 2024 • Mathias Viborg Andersen, Ross Greer, Andreas Møgelmose, Mohan Trivedi
The findings suggest the potential of generative models in addressing missing frames, advancing driver state monitoring for intelligent vehicles, and underscoring the need for continued research in model generalization and customization.
no code implementations • 11 Feb 2024 • Ross Greer, Mohan Trivedi
From the generated clusters, we further present methods for generating textual explanations of elements which differentiate scenes classified as novel from other scenes in the data pool, presenting qualitative examples from the clustered results.
1 code implementation • 5 Feb 2024 • Ahmed Ghita, Bjørk Antoniussen, Walter Zimmer, Ross Greer, Christian Creß, Andreas Møgelmose, Mohan M. Trivedi, Alois C. Knoll
We propose ActiveAnno3D, an active learning framework to select data samples for labeling that are of maximum informativeness for training.
no code implementations • 30 Jan 2024 • Ross Greer, Bjørk Antoniussen, Mathias V. Andersen, Andreas Møgelmose, Mohan M. Trivedi
Active learning strategies for 3D object detection in autonomous driving datasets may help to address challenges of data imbalance, redundancy, and high-dimensional data.
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 • 30 Jan 2023 • Ross Greer, Mohan Trivedi
Multi-sensor frameworks provide opportunities for ensemble learning and sensor fusion to make use of redundancy and supplemental information, helpful in real-world safety applications such as continuous driver state monitoring which necessitate predictions even in cases where information may be intermittently missing.
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.
no code implementations • 14 Jan 2023 • Ross Greer, Lulua Rakla, Anish Gopalan, Mohan Trivedi
Manual (hand-related) activity is a significant source of crash risk while driving.
no code implementations • 14 Jan 2023 • Ross Greer, Nachiket Deo, Akshay Rangesh, Pujitha Gunaratne, Mohan Trivedi
To make safe transitions from autonomous to manual control, a vehicle must have a representation of the awareness of driver state; two metrics which quantify this state are the Observable Readiness Index and Takeover Time.
no code implementations • 25 May 2022 • Ross Greer, Mohan Trivedi
We demonstrate the algorithmic performance by analyzing three real-world datasets containing multiple periods of data collection for four-corner and two-corner intersections with marked and unmarked crosswalks.
no code implementations • 2 Dec 2021 • Ross Greer, Jason Isa, Nachiket Deo, Akshay Rangesh, Mohan M. Trivedi
Safe path planning in autonomous driving is a complex task due to the interplay of static scene elements and uncertain surrounding agents.
no code implementations • 27 Jul 2021 • Akshay Rangesh, Nachiket Deo, Ross Greer, Pujitha Gunaratne, Mohan M. Trivedi
Using the augmented dataset, we develop and train take-over time (TOT) models that operate sequentially on mid and high-level features produced by computer vision algorithms operating on different driver-facing camera views, showing models trained on the augmented dataset to outperform the initial dataset.
no code implementations • 23 Apr 2021 • Akshay Rangesh, Nachiket Deo, Ross Greer, Pujitha Gunaratne, Mohan M. Trivedi
With increasing automation in passenger vehicles, the study of safe and smooth occupant-vehicle interaction and control transitions is key.
no code implementations • 12 Nov 2020 • Ross Greer, Nachiket Deo, Mohan Trivedi
Predicting a vehicle's trajectory is an essential ability for autonomous vehicles navigating through complex urban traffic scenes.