#95 Computer Aided Design for Safe Autonomous Vehicles
- Principal Investigator
- Rahul Mangharam
- Status
- Overdue Project
- Start Date
- July 1, 2017
- End Date
- June 30, 2023
- Project Type
- Research Applied
- Grant Program
- FAST Act - Mobility National (2016 - 2022)
- Grant Cycle
- Mobility21 - University of Pennsylvania
- Visibility
- Public
Abstract
Objective
This project focuses on establishing a systematic set of testing benchmarks to ensure the safety of an autonomous vehicle given its perception, planning and control systems. We will design an autonomous vehicle computer-aided design (CAD) toolchain, which captures formal descriptions of driving scenarios in order to develop a safety case for an autonomous vehicle (AV). Rather than focus on a particular component of the AV, like adaptive cruise control, the toolchain models the end-to-end dynamics of the AV in a formal way suitable for testing and verification.
Description
Methodology First, a domain-specific language capable of describing the scenarios that occur in the day-to-day operation of an AV is defined. The language allows the description and composition of traffic participants, and the specification of formal correctness requirements. A scenario described in this language is an executable that can be processed by a specification-guided automated test generator (bug hunting), and by an exhaustive reachability tool. The toolchain allows the user to exploit and integrate the strengths of both testing and reachability, in a way not possible when each is run alone. Finally, given a particular execution of the scenario that violates the requirements, a visualization tool can display this counter-example and generate labeled sensor data.
Timeline
1. Develop toolchain 2. Evaluate real visual image data sets with simulator data sets 3. Create multiple driving scenarios and complete safety analysis on an interactive website
Strategic Description / RD&T
Deployment Plan
Deliverables The effectiveness of the approach will be demonstrated on five autonomous driving scenarios drawn from a collection of 36 scenarios that account for over 95% of accidents nationwide.
Expected Outcomes/Impacts
These case studies will demonstrate robustness-guided verification heuristics to reduce analysis time, counterexample visualization for identifying controller bugs in both the discrete decision logic and low-level analog (continuous) dynamics, and identification of modeling errors that lead to unrealistic environment behavior.
Expected Outputs
TRID
Individuals Involved
| Name | Affiliation | Role | Position | |
|---|---|---|---|---|
| rahulm@seas.upenn.edu | Mangharam, Rahul | University of Pennsylvania | PI | Faculty - Tenured |
| mokelly@seas.upenn.edu | O'Kelly, Matthew | University of Pennsylvania | Other | Student - PhD |
Budget
Amount of UTC Funds Awarded
$363197.00Total Project Budget (from all funding sources)
$363197.00Documents
Match Sources
No match sources!
Partners
No partners!