Self-driving Uber in fatal crash did not know people could jaywalk

Vehicle had failed to properly identify pedestrian, National Transportation Safety Board concludes

A self-driving Uber test vehicle that killed a woman in the first fatal accident of its kind, was not programmed to recognise people crossing the road, an investigation has revealed.

Elaine Herzberg, 49, was struck on the night of 18 March 2018, as she crossed a road in the city of Tempe, Arizona, with her bicycle.

The crash in Arizona last year was the result of software flaws with the vehicle, according to the US National Transportation Safety Board (NTSB), which said in a report that the Uber Technologies Inc vehicle had failed to properly identify her as a pedestrian.

These flaws had also contributed to 37 other incidents in the 18 months leading up to the crash, it said.

The NTSB may now use the findings to make recommendations which could impact how the entire industry addresses self-driving software issues or to regulators about how to oversee the industry.

The board will meet 19 November to determine the probable cause of the March 2018 accident, but has published the report ahead of that.

That accident prompted significant safety concerns about the nascent self-driving car industry, which is working to get vehicles into commercial use.

In the aftermath of the crash, Uber suspended all testing and did not resume until December in Pennsylvania with revised software and significant new restrictions and safeguards,

Sarah Abboud, a spokesperson for Uber's self-driving car effort, said the company regretted the crash that killed Herzberg.

She said the company had "adopted critical program improvements to further prioritise safety. We deeply value the thoroughness of the NTSB's investigation into the crash and look forward to reviewing their recommendations."

The NTSB reported at least two prior crashes in which Uber test vehicles may not have identified roadway hazards. Between September 2016 and March 2018, there were 37 crashes of Uber vehicles in autonomous mode, including 33 that involved another vehicle striking test vehicles.

On one occasion the test vehicle struck a bent bicycle lane post that partially occupied the test vehicle's lane of travel. In another incident, the operator took control to avoid a rapidly approaching vehicle that entered its lane of travel. The vehicle operator steered away and struck a parked car.

NTSB said Uber conducted simulation of sensor data from the Arizona crash with the revised software and told the agency the new software would have been able to detect the pedestrian 88 meters (289 feet) or 4.5 seconds before impact. The car's system would have started to brake four seconds before impact.

In the real accident involving Ms Herzberg, the test vehicle did not correctly identify the bicycle as an imminent collision until 1.2 seconds before impact. By then it was too late for the Uber car to avoid the crash.

"The system design did not include a consideration for jaywalking pedestrians," NTSB said.

The Uber car also initiated a one-second delay of planned braking while the vehicle calculated an alternative path or the safety driver could take over. Uber has since discontinued that function as part of its software update.

NTSB during its investigation it "communicated several safety-relevant issue areas (to Uber) that were uncovered during the course of the investigation."

In March, prosecutors in Arizona said Uber was not criminally liable in the self-driving crash.

Police have investigated whether the safety driver who was behind the wheel and supposed to respond in the event of an emergency should face criminal charges.

Investigators have said the crash was "entirely avoidable" and that the backup driver was watching The Voice TV program at the time of the crash.

The accident was the first reported incident of a self-driving car killing a pedestrian and has raised questions about the future of autonomous vehicle safety.

Uber said it is working with the NTSB to better understand and improve safety for its self-driving car program.

Additional reporting from agencies