Candidate: Barry Gilhuly
Date: November 15, 2023
Time: 10:00 AM
Place: E5 4047
Supervisor(s): Smith, Stephen L
Abstract:
Visibility is a crucial aspect of planning and control of autonomous vehicles (AV), particularly when navigating environments with occlusions. However, when an AV follows a trajectory with multiple occlusions, existing methods evaluate each occlusion individually, calculate a visibility cost for each, and rely on the planner to minimize the overall cost. This can result in conflicting priorities for the planner, as individual occlusion costs may appear to be in opposition. We solve this problem by creating a perspective cost map that allows for an aggregate view of the occlusions in the environment. The value of each cell on the cost map is a measure of the amount of visual information that the vehicle can gain about the environment by visiting that location. Our proposed method identifies observation locations and occlusion targets drawn from both map data and sensor data. We show how to build a probabilistic perspective grid for each observation location and then combine all grids into one perspective cost map for motion planning. We also show that, by directly planning for future occlusions, we produce a more accurate assessment of the visible regions of the environment and thus plan a smoother path for the AV, compared to existing methods.