Timezone: »

 
Poster
Risk-Driven Design of Perception Systems
Anthony Corso · Sydney Katz · Craig Innes · Xin Du · Subramanian Ramamoorthy · Mykel J Kochenderfer

Wed Nov 30 09:00 AM -- 11:00 AM (PST) @ Hall J #928
in Poster Session 3 »

Modern autonomous systems rely on perception modules to process complex sensor measurements into state estimates. These estimates are then passed to a controller, which uses them to make safety-critical decisions. It is therefore important that we design perception systems to minimize errors that reduce the overall safety of the system. We develop a risk-driven approach to designing perception systems that accounts for the effect of perceptual errors on the performance of the fully-integrated, closed-loop system. We formulate a risk function to quantify the effect of a given perceptual error on overall safety, and show how we can use it to design safer perception systems by including a risk-dependent term in the loss function and generating training data in risk-sensitive regions. We evaluate our techniques on a realistic vision-based aircraft detect and avoid application and show that risk-driven design reduces collision risk by 37% over a baseline system.

Keywords: Perception · Object Detection · risk-sensitivity · aircraft collision avoidance · Safety-critical autonomy
[ Paper]  [ Poster]  [ OpenReview] 

Author Information

Anthony Corso (Stanford University)
Sydney Katz (Stanford University)
Craig Innes (Edinburgh University, University of Edinburgh)
Xin Du (University of Edinburgh)
Subramanian Ramamoorthy (The University of Edinburgh)
Mykel J Kochenderfer (Stanford University)

More from the Same Authors