What humanlike errors do autonomous vehicles need to avoid to maximize safety?

The final failure in the causal chain of events in 94% of crashes is driver error. It is assumed most crashes will be prevented by autonomous vehicles (AVs), but AVs will still crash if they make the same mistakes as humans. By identifying the distribution of crashes among various contributing factors, this study provides guidance on the roles AVs must perform and errors they must avoid to realize their safety potential. Using the NMVCCS database, five categories of driver-related contributing factors were assigned to crashes: (1) sensing/perceiving (i.e., not recognizing hazards); (2) predicting (i.e., misjudging behavior of other vehicles); (3) planning/deciding (i.e., poor decision-making behind traffic law adherence and defensive driving); (4) execution/performance (i.e., inappropriate vehicle control); and (5) incapacitation (i.e., alcohol-impaired or otherwise incapacitated driver). Assuming AVs would have superior perception and be incapable of incapacitation, the authors determined how many crashes would persist beyond those with incapacitation or exclusively sensing/perceiving factors. Thirty-three percent of crashes involved only sensing/perceiving factors (23%) or incapacitation (10%). If they could be prevented by AVs, 67% could remain, many with planning/deciding (41%), execution/performance (23%), and predicting (17%) factors. Crashes with planning/deciding factors often involved speeding (23%) or illegal maneuvers (15%). Errors in choosing evasive maneuvers, predicting actions of other road users, and traveling at speeds suitable for conditions will persist if designers program AVs to make errors similar to those of today’s human drivers. Planning/deciding factors, such as speeding and disobeying traffic laws, reflect driver preferences, and AV design philosophies will need to be consistent with safety rather than occupant preferences when they conflict. This study illustrates the complex roles AVs will have to perform and the risks arising from occupant preferences that AV designers and regulators must address if AVs will realize their potential to eliminate most crashes.

• Record URL:
  https://doi.org/10.1016/j.jsr.2020.10.005
• Record URL:
  http://www.sciencedirect.com/science/article/pii/S0022437520301262
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/oclc/1800052
• Supplemental Notes:
  • © 2020 National Safety Council and Elsevier Ltd. All rights reserved. Abstract reprinted with permission of Elsevier.
• Authors:
  • Mueller, Alexandra S
  • Cicchino, Jessica B
  • Zuby, David S S
• Publication Date: 2020-12

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 310-318
• Serial:
  • Journal of Safety Research
  • Volume: 75
  • Issue Number: 0
  • Publisher: Elsevier
  • ISSN: 0022-4375
  • Serial URL: http://www.sciencedirect.com/science/journal/00224375

Subject/Index Terms

• TRT Terms: Autonomous vehicles; Crash causes; Decision making; Highway safety; Human error; Vehicle design; Vehicle factors in crashes
• Subject Areas: Design; Highways; Safety and Human Factors; Vehicles and Equipment;

Filing Info

• Accession Number: 01762142
• Record Type: Publication
• Files: TRIS
• Created Date: Dec 3 2020 3:12PM