Milo Henry Lovelace Knowles
MIT AeroAstro | Lincoln Laboratory Undergraduate Research and Innovation Scholar
Research Project Title:
Semantic SLAM for Dynamic Object Motion Estimation
abstract:Many autonomous robots, such as self-driving cars, must navigate through and interact with dynamic environments. Commonly used approaches in SLAM and visual odometry assume a static world, which can lead to inaccurate scene reconstructions and pose estimates if many dynamic objects are present. This project aims to mitigate these issues by tracking and modelling the motion of dynamic objects in a scene. By incorporating an object detector into our SLAM pipeline, we can detect dynamic objects in a scene and mask them during feature tracking. In addition, we can fuse temporal measurements of each object over time to infer its motion. These motion estimates can then be used for predictive planning and obstacle avoidance.
Working as UROP student in the Robust Robotics Group for the past two years has given me a lot of exposure to current research in autonomous robotics, especially perception. I'm excited to continue exploring this area of robotics through my SuperUROP, and publish or present results.