News
The AI Seminar is a weekly meeting at the University of Alberta where researchers interested in artificial intelligence (AI) can share their research. Presenters include both local speakers from the University of Alberta and visitors from other institutions. Topics can be related in any way to artificial intelligence, from foundational theoretical work to innovative applications of AI techniques to new fields and problems.
On July 28th, Shahin Atakishiyev — a PhD student at the University of Alberta — presented “Explaining Autonomous Driving Actions with Visual Question Answering" at the AI Seminar.
The end-to-end learning ability of self-driving vehicles has achieved significant milestones over the last decade owing to rapid advances in deep learning and computer vision algorithms. However, as autonomous driving technology is a safety-critical application of artificial intelligence (AI), road accidents and established regulatory principles necessitate the need for the explainability of intelligent action choices for self-driving vehicles.
To facilitate interpretability of decision-making in autonomous driving, Atakishiyev presents a Visual Question Answering (VQA) framework, which explains self-driving actions with question-answering-based causal reasoning. To do so, he first collects driving videos in a simulation environment using reinforcement learning (RL) and extract consecutive frames from this log data uniformly for five selected action categories. Further, Atakishiyev manually annotates the extracted frames using question-answer pairs as justifications for the actions chosen in each scenario. Finally, he evaluates the correctness of the VQA-predicted answers for actions on unseen driving scenes. The empirical results suggest that the VQA mechanism can provide support to interpret real-time decisions of autonomous vehicles and help enhance overall driving safety.
Watch the full presentation below:
Want to learn how you can kick-start your AI career? Find out more about Amii's Career Accelerator to find out more.
Jul 24th 2024
News
How do we get the best results when AI and human beings work together? In this episode of Approximately Correct, we’re looking into Human-In-The-Loop AI with Amii Fellow and Canada CIFAR AI Chair Matt Taylor.
Jul 22nd 2024
News
Read our monthly update on Alberta’s growing machine intelligence ecosystem and exciting opportunities to get involved.
Jul 18th 2024
News
Amii announces work with Communitech, a Waterloo Region innovation hub, to empower startup founders with the AI tools and resources they need to integrate AI and build in-house capabilities successfully. The collaboration will leverage Amii’s leading AI expertise and resources and be centred around Amii’s Machine Learning Exploration (ML Exploration) program.
Looking to build AI capacity? Need a speaker at your event?