Seminars

Autonomous vehicles rely on 3D perception to understand their surrounding environment. Although there has been remarkable progress in enhancing the accuracy of perception models, their efficiency still lags behind real-time performance, impeding their use in real-world applications.

In this lecture, I will present our recent work, BEVFusion (ICRA 2023), which facilitates efficient multi-task multi-sensor fusion by…

Multi-robot systems have many appealing applications such as shape formation, search and rescue, surveillance and reconnaissance, cooperative target tracking, and collective transport. However, even the presence of a few faulty or malicious robots can easily disrupt the overall function and safety of the swarm. In this talk, I will present a novel method for achieving Byzantine resilience in large robot swarms. We consider Byzantine robots which are an unknown subset of robots that are allowed to have arbitrarily different behaviors relative to cooperative robots in terms of…

Inspired by the potential of artificial intelligence (AI) to improve access to expert-level medical image interpretation, several organizations began developing deep learning-based AI systems for detecting diabetic retinopathy (DR) from retinal fundus images around 2015. Today, these AI-based tools are finally being deployed at scale in certain parts of the world, often bringing DR screening to a population lacking easy access to timely diagnosis. The path to translating AI research into a useful clinical tool has gone through several unforeseen challenges along the way. In this talk, we…

With the release of ChatGPT last November, it has sparked a global interest in this new technology and Generative AI as a whole. In this talk, I will provide a briefing of the foundational technology behind Generative AI. More importantly, from industry perspective, I will discuss the limitations and challenges of Generative AI that must be overcome in order for this technology to be widely deployable. Since running these large Generative AI models are very expensive and maybe out of reach for many companies and universities, I will share my thoughts on the areas that companies and…

The goal of autonomous driving systems (ADS) research is to give safer and economical mobility options. However, the operational design domains (ODD) of state-of-the-art ADS constraints the deployment under sunny to cloudy conditions. The weather phenomena impair the perception and navigation capabilities of ADS, so their availability is limited by geography and seasons. Furthermore, unstable vehicle control induces a strong feeling of risk to the passengers. For ADS to continue moving forward to the next era, research efforts are necessary to enable autonomous cars to get past all the…