They also addressed the earlier flaw that all the path history was lost every time the object classification changed:

>Path Prediction. ATG changed the way the ADS generates possible trajectories—predicts the path—of detected objects (as described in section 1.6.1). Previous locations of a tracked object are incorporated into decision process when generating possible trajectories, even when object’s classification changes. Trajectories are generated based on both (1) the classification of the object–possible goals associated with such object, and (2) the all previous locations.

edit: This was also improved, clearly it was not ready when it rolled-out before these changes:

>Volvo provided ATG with an access to its ADAS to allow seamless automatic deactivation when engaging the ADS. According to ATG and Volvo, simultaneous operation of Volvo ADAS and ATG ADS was viewed as incompatible because (1) of high likelihood of misinterpretation of signals between Volvo and ATG radars due to the use of same frequencies; (2) the vehicle’s brake module had not been designed to assign priority if it were to receive braking commands from both the Volvo AEB and ATG ADS.

... changes

>Volvo ADAS. Several Volvo ADAS remain active during the operation of the ADS; specifically, the FCW and the AEB with pedestrian-detection capabilities are engaged during both manual driving and testing with the UBER ATG autonomous mode. ATG changed the frequency at which ATG-installed radars supporting the ADS operate; at the new frequency, these radars do not interfere with the functioning of Volvo ADAS. ATG also worked with Volvo to assign prioritization for the ADS and Volvo AEB in situations when both systems issue command for braking. The decision of which system is assigned priority is dependent on the specific circumstance at that time.Volvo ADAS. Several Volvo ADAS remain active during the operation of the ADS; specifically, the FCW and the AEB with pedestrian-detection capabilities are engaged during both manual driving and testing with the UBER ATG autonomous mode. ATG changed the frequency at which ATG-installed radars supporting the ADS operate; at the new frequency, these radars do not interfere with the functioning of Volvo ADAS.

>ATG also worked with Volvo to assign prioritization for the ADS and Volvo AEB in situations when both systems issue command for braking. The decision of which system is assigned priority is dependent on the specific circumstance at that time.

Jerk is the rate of change of deceleration. The original settings were a pause of 1s, followed by 5m/s³ of jerk up to 7m/s². That means it takes 2.4s from the issue is detected until "full" braking of 7m/s² is applied.

Even 20m/s³ doesn't seem all that aggressive to me. A good car can brake with around 9m/s² (depending on the state of the road) which means it's going to take 0.45s to go from 0 to full braking.

Too bad they didn't do that after any of the previous 33 times it crashed into a vehicle

There's lots of bad stuff in this story without making up new stuff. Those 33 times were other vehicles striking the Uber vehicle, rather than vice versa. There was one time where the Uber vehicle struck a stationary bicyle stand that was in the roadway.

Is the story wrong? This is what it says:

"In these 37 incidents, all of the robo-vehicles were driving in autonomous mode, and in 33, self-driving cars crashed into other vehicles."

This is saying the self-driving cars crashed into other vehicles.

Story is wrong. The linked report has it as "Most of these crashes involved another vehicle striking the ATG test vehicle—33 such incidents; 25 of them were rear-end crashes and in 8 crashes ATG test vehicle was side swiped by another vehicle."

Edit: I emailed the register and they fixed it immediately. Nice!

That doesn't say who's at fault. Could be that Uber got rear ended 25 times before they disabled emergency breaking, then they hit a pedestrian.

I agree. Just pointed out that it is patched now...or rather, should be.