C18501: Tiger Taxi


Rochester Institute of Technology

Department of Computer Engineering

Senior Design Project — Fall 2018

Project Name: Tiger Taxi

Team: Kenneth Alexopoulos, Zachariah Carmichael, Frank Cwitkowitz, & Benjamin Glasstone

Welcome to the Den of the Tiger Taxi1

Self-driving of autonomous robots and vehicles require agents to learn and maintain accurate maps for safe and reliable operation. We use a variant of pose-graph Simultaneous Localization and Mapping (SLAM) to integrate multiple sensors for autonomous navigation in an urban environment. Our methods efficiently and accurately localize the agent across a map generated from different sensors across different periods of time. To incorporate a priori localization data, we propose an amendment of the pose-graph error function by accounting for error between observations and publicly available building geometry. We fuse data derived from heterogeneous sensor modalities using extended Kalman filters to increase invariance to dynamic environmental factors, such as weather, luminance, and occlusion. To discriminate traversable terrain, we employ a deep segmentation network whose predictions increase confidence of a LiDAR-generated cost map. Path planning is accomplished using the Timed-Elastic-Band algorithm on the persistent map created through SLAM. We evaluate our method in varying environmental conditions on a large university campus and show the efficacy of the sensor and map fusion.

1Project has been known as the "Autonomous People Mover" in the past.


Project Details