Research

Multi-Medium Semantic SLAM for Sparse Environments (Dec 2021 - Sept 2022)
Karter Krueger, Zhentian Qian, Jing Xiao (AIR Lab)
(Submitted to ICRA 2023)

• Existing SLAM methods fail to accurately track in feature-repetitive sparse environments

• We combined low-level and high-level features such as semantically-important lines & points, planes, and objects (such as windows), in addition to the low-level ORB features

• Our method reduced the tracking error by 70% compared to ORB-SLAM2 in sparse environments

DigSafe Autonomous Cable Detection Robot (Aug 2021 - May 2022)
Industry-Sponsored Research (AIR Lab)

• This project was sponsored by Eversource Utilities to create a novel robot that could autonomously detect, follow, and mark buried electrical cables prior to construction operations

• Our robot detected buried cables using a Vivax Locator searching for the 60hz frequency range

• Sensor fusion was performed on data from LiDAR, IMU, encoders, and GPS to navigate

Interpretable UAV Collision Avoidance using Deep RL (Jan 2021 - May 2022)
Deepak-George Thomas, Daniil Olshanskyi, Karter Krueger, Tichakorn Wongpiromsarn, Ali Jannesari
(Arxiv 2021)

• A multi-head self-attention Graph Neural Network was used with a D3QN RL learning policy to detect and avoid obstacles with an RGBD camera on a simulated drone in Unreal Engine

Tetrahedron Object Tracking (Nov 2019 - May 2020)
Parallel to the vision tracking aspect of this paper by Matthew Gardner and Yan-Bin Jia
(I presented at the 2022 Iowa State University Honors Research Symposium [video])

• A custom vision pipeline was implemented to detect and track the corners and edges of a white tetrahedron object tossed across a low-light environment