Research @ ESP
Research @ ESP
The Estimation, Search, and Planning (ESP) research group is focused on improving our understanding of robotic fundamentals. We use this understanding to develop and deploy theoretically well-founded solutions to academic and real-world robotic problems, especially in the context of complex and dynamic environments.
We are primarily interested in problems arising in state estimation, task scheduling and search, and motion and path planning but we study any topic in robotics. We use a knowledge-driven research approach that is based on theoretical rigour and experimental validation and is often done with in collaboration with external partners.
Marlin has been working on planning problems that seek to optimize the distance between paths and obstacles. This is a difficult problem for informed search algorithms, like A*, because there aren't very many effective and cost-efficient admissible… https://t.co/DbrdHZ5k4u
Another ESP paper at virtual IROS is Rowan's latest work on NBV planning for autonomous 3D reconstruction. It presents an updated Surface Edge Explorer (SEE++) algorithm that considers more information and is available as open source code. If you'd like… https://t.co/hoOaM5F7S1
ESP has three papers at IROS this year, which is being held virtually as an on-demand conference. All our work is already available and includes Kevin's most recent paper on occlusion-robust Multimotion Visual Odometry (MVO). You can watch a short video… https://t.co/VDdNguR72j
Jonathan was invited to survey the popular field of asymptotically optimal sampling-based motion planning algorithms in the Annual Review of Control, Robotics, and Autonomous Systems. The paper will be published in 2021, but you can read a preprint of it… https://t.co/6Ghgy2KUbl
Rowan has a great new paper on how to estimate occlusions and view coverage in density-based next best view (NBV) algorithms at IROS 2020. The full paper is already available on arXiv and you can also download the code to try it yourself. https://t.co/AJt64BxCKw