DeepAI
Log In Sign Up

Risk-Driven Design of Perception Systems

05/21/2022
by   Anthony L. Corso, et al.
0

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

READ FULL TEXT

page 5

page 6

page 7

page 9

page 15

07/21/2021

Risk-Based Safety Envelopes for Autonomous Vehicles Under Perception Uncertainty

Ensuring the safety of autonomous vehicles, given the uncertainty in sen...
04/25/2018

Design and Evaluation of a Novel Cable-Driven Gripper with Perception Capabilities for Strawberry Picking Robots

This paper presents a novel cable-driven gripper with perception capabil...
09/09/2021

Risk-perception-aware control design under dynamic spatial risks

This work proposes a novel risk-perception-aware (RPA) control design us...
06/14/2022

Architectural patterns for handling runtime uncertainty of data-driven models in safety-critical perception

Data-driven models (DDM) based on machine learning and other AI techniqu...
09/30/2021

Simulation Based Probabilistic Risk Assessment (SIMPRA): Risk Based Design

The classical approach to design a system is based on a deterministic pe...
02/19/2019

Predicting city safety perception based on visual image content

Safety perception measurement has been a subject of interest in many cit...
09/20/2022

Testing Rare Downstream Safety Violations via Upstream Adaptive Sampling of Perception Error Models

Testing black-box perceptual-control systems in simulation faces two dif...