Welcome to the Estimation, Search, and Planning (ESP) research group, a member of the Ingenuity Labs Research Institute and the Department of Electrical and Computer Engineering (ECE) in Smith Engineering at Queen's University. We motivate a knowledge-based approach to robotics research by taking on challenging, real-world problems. We do this to test our solutions and force us to understand the fundamental challenges of next-generation robots.
Please have a look around our website to find out more about who we are and what we do, including our publicly available code and datasets. You may also be interested in our YouTube, Bluesky, and GitHub accounts.
Tyler Wilson presented his work on Fully Connected Informed Trees (FCIT*) at ICRA 2025 in Atlanta, Georgia. You can already read the paper on arXiv, watch a short video on YouTube, and checkout the code yourself.
While there, Tyler also presented an early preview of our recent RA-L submission on asymptotically optimal RRT-Connect (AORRTC), which you can read more about here.
Tyler has an exciting new work that achieves orders-of-magnitude faster asymptotically optimal planning with and without hardware acceleration. This work is with Wil Thomason and Zak Kingston (CoMMA Lab, Purdue University) and is under review at RA-L and an early release will be presented at the RoboARCH workshop at ICRA 2025. You can can watch the video on YouTube, read the paper on arXiv, and checkout both the VAMP and OMPL code.
Tyler and Jonathan have been working with Wil Thomason (The AI Institute), Zak Kingston (CoMMA Lab, Purdue University), and Lydia Kavraki (Kavraki Lab, Rice University) on extending their exciting work on vector accelerated motion planning (VAMP). Fully Connected Informed Trees (FCIT*) uses SIMD instructions to achieve real-time almost-surely asymptotically optimal planning and has been submitted to ICRA 2025. If you'd like to know more you can watch the trailer video on YouTube, read the paper on arXiv, and checkout the code.
