Self-Driving Uber Death: Role Of Video And AI

John Honovich

The self-driving Uber death has caused significant debate about the future and safety of self-driving cars. The car's video is a key factor in it.

Here are the video recordings of the road and driver just prior to the crash:

And here is a snapshot from the car camera a second or two before the crash:

The scene looks dark but a key issue is how dark it actually was for human vision. The issue is that car cams generally are significantly worse in low light than the human eye (e.g., Testing CarCam). Many are commenting on this using the darkness of the video as reference but how dark it really was for the operator is a key issue. Also, the operator appears to be looking down.

The final issue is the car's self-driving system most certainly does not depend on visible light sensors so why did it miss this person?

Login to read this IPVM discussion.

Why do I need to log in?

IPVM conducts unique testing and research funded by member's payments enabling us to offer the most independent, accurate and in-depth information.

John Honovich

IPVM | 03/22/18 01:36pm

***,** **** *****, **** *** ***:

*** **** ********’* ******** ********** *** **** **** ********. ** Monday, ***** ***. ****** ****** ********** ****’* ******** ** ****** Vasquez. ** ***’* ***** *** **** **. ******* *** **** at ****, *** ** ******’* ** ******* ********* *** *******.
** *** ********* *** ***** * ****-**** ******** ** ******** County *** ********* ***** ******* ** ****, ********* ** ******* Department ** *********** *******, * ******** ****** ************ **** * one-year ******** *** * **** ***** ********* **********.
** **** *** ******* **********, ******** ****** ** **** ** driving **** * *********, ******* ** ******** ******* ** ****** Municipal *****, *** ** **** *** ***** *** ******* ** produce ***** ** ********* *** ******* ******* * ******* ************.

Undisclosed #1

03/22/18 02:03pm

* *****'* **** **** *** ******* ** **** ******** ***, but ** ******* *'* ********* *** *** ******* *** *** pick ** *** **********/*******. ***'* **** ********* **** ***** *** other ******* ******* ******** **** *** **** *******? *** ******* are ****** ***** *** ***** ***, ** * ***'* ******* the *** ***** *** ************ ********* ***** ** **** ****** lit *****.

*'** **** ** **** ** ** *** *** **** **** because ** *** ***** ** *** ********** ** *** ** to *** ****** ***** ** ******'* **** ** **** *****'*.

***** *** ********'* ******** ********** *** ****** ** ** **** this ********, *** **** ***** ******* **** **** ********** *** this *** ** ****** **.

Undisclosed #3

In reply to Undisclosed #1 | 03/22/18 04:56pm

***'* **** ********* **** *****

***, *** ***** ***** ******* ** ************ ** *******, *** some ******** *** ********** **** ************. ****** ****, *** **** have *** "**" ******* **** ******* *** ***** ***** **** from ***** **** "*******", ***** *** ** *********** ** ***** where *** **** **** ************, ** **** * ***** ***** lens.

* ***'* **** **** *** ******** ** **** ****, *** lidar *** **** ***********, ****** * ***** **** ******** **** at **** ***** *****, *** ***** ***** **** ** ***** known ***** *** **** **** ** ***** ****** *****. **** the ******** ***** ** ***** **** ********** **** **** *** **** ** *** ******* ** * potential ***** *****-****, ********* ** *** *** ******* **** ******** on *** *******.

Brian Rhodes

IPVMU Certified | 03/22/18 02:43pm

*** ******* ****** ** ** **** *** *** ***** *** most ******* **** ** ****-******* ****: ** *** *** **** people.

** ** * *** ********, *** **** **/**** **** ****** the ******** *** *******, *****'* ***** ** ** ****** *** distrust ****-******* **** ** * ******* *********.

Undisclosed #1

In reply to Brian Rhodes | 03/22/18 02:56pm

******. **** *** *** **** ******* **** *** ** *** road, *** ***** ** ***** ** ** *********** ***********. ********* it **** ** ***** **** **** **** **** ******* **** will **** ***** ********* *** ****** ******** ** ***** ******** vehicles.

********** * **** *** **** ** *** ****-******* ******* ********* working ******** ** * ******** ********/** ** ***** *** *** vehicles ** **** * ******* *** ******* ****** ***** ** safety. **** *** ** *********** ** ****, *** ************* ***** be **** ** ****** ***** **** **************. * ***'* **** the **** **** ****** ** ***** ***** **** *** **** system *** **** ***** ** ******* ** *** **** **** software/hardware ** ***** ****.

Undisclosed #2

In reply to Brian Rhodes | 03/22/18 04:52pm

...*** *** ***** *** **** ******* **** ** ****-******* ****: Do *** *** **** ******.

*** ** **** ****** *** ***** ****? **** ***** *** safety ** *** ******/**********?

**************, ****** * ****-******* ***, **** ****** ** ***, ******* to ****** ** **** ***** ** ***** * ********?

Brian Rhodes

IPVMU Certified | In reply to Undisclosed #2 | 03/22/18 05:00pm

**** * ********* ******* ** *** ** *** ****** ******* they ******** * ***********?

*'* *** ****** *** ***** ** **********, *** ***** *** occupants *** ** *** *** ********* (*** **** ******* ** taxi ** ***** **** ***** *********) *** ********** **** ** authority **** *** *** ***** ***** ** **, ** ***** preventing ****** ** ********** ** ********* *********.

Undisclosed Manufacturer #4

In reply to Brian Rhodes | 03/22/18 07:41pm

*** **** * ***% ***** **** **** ***** **** ***** [if *'* ************* ** *********]. ********** *** ********* *** ** fault ** *** ** *** ***. ** ** ***** *** to ** * ******** ********** ** ***** ******* ** ****-****** [dangerous ** ********** *** ***** ********] ** * **** ***** simple **** ******* ******, ** ***** ** ** *** ****** would ** ********** ** *** ******.

**** *****'* ***** ** *** **** *** ** ******* ** be **** ****** *** ******* ****** **** ********, *** ** was ***** * ****** ** *** ****** *** ** *** middle ** ******* ** * **** *****. * ****** *** tragedy ***** ***** **** ********** **** ***** ******* ******** ** hybrid ***/******* ** ***** **********.

Undisclosed #2

03/22/18 04:31pm

*** ***** ***** ** *** ***'* ****-******* ****** **** ********* does *** ****** ** ******* ***** *******...

****:**** * ****-******* *** **** - ***** ***** *********

John Honovich

IPVM | 03/25/18 06:49pm

*** ***** ******** *** *** **** ******* ********* *** ***** ** ****:

*********, *** ***** ** ******* ** ******* ******* ****** *** her ******* ** **** *********. *******, *** ***** *****’* **** the ******** ** *** ** *** ****** ** *** *** of *** ***.
** ******** ** *****, ********** ******* ********* **** ******* *******, including ****** *** ***** ** **** *********. ** ***’* **** what ******* **** ** *** **** *** **** *******, ** they **** *******, ** *** **** **** ***** ****.

Undisclosed #2

In reply to John Honovich | 03/25/18 10:12pm

*** ***** ******** *** *** **** ******* ** ******* *** blame ** ****:

***** ******** **** ****:

“* *** *** **** **** ********** **** ** ********** **** that *** **** *********** — ** **** **** * ********** with * ******* — ** **** * *** ** ********** that *** ********** ***** ** ****** *** ***** ** **** to ****** ********** **** ****,” ******* **** ******** ****** * panel ** *** ******** ********** ******* *********** ********** ** *** Vegas.

Undisclosed #2

05/29/18 09:09am

******:****** ******** **** *** *****

********* ** *** **** ******, *** **** ******* ********* ** identify ****** ******** ** *** ******* *** ******* ****** * four-lane ****. ******** ** *** ****, *** ***’* ***** *** LIDAR ******** *** *** ******* ****** *** *****. *** *** perception ****** *** ********: ** ********** *** ** ** ******* object, **** ** * ******* *** ******* ** * *******, whose **** ** ***** *** *******.
**** *.* ******* ****** ******, *** ****-******* ****** ******** **** emergency ******* *** ******. *** *** ***’* *****-** ********* ******* system *** **** ********, ** ******* ******** **** *** ****-******* system; ******* * ***** ****** ******** ** *** ******* ** expected ** ***** **** ******. *** *** ****** ********, *** had **** ******* **** ** *** ****-******* ******’* ******* ******, failed ** ***** ** ****...

John Honovich

IPVM | In reply to Undisclosed #2 | 05/29/18 11:50am

** ********** *** ** ** ******* ******, **** ** * vehicle *** ******* ** * *******, ***** **** ** ***** not *******.

* ****** ******* * ******* ** ****** ** **** **** that *** ********* ** *** ****** *** *** **********. ****'* not ** ****** **** *** ** ***** *** *** ************ of ******** * ****** **** ***** ***** ******* ****-***** **********.

Discussion	Posts	Latest
Upcoming Mobile App Shootout - What Criteria Should Be Considered? (11) Started by Sean Patton	11	about 1 hour by Undisclosed Manufacturer #4
Where Are The Pre/Post Motion Settings On Milestone? (6) Started by Undisclosed Manufacturer #1	6	about 1 hour by Undisclosed Manufacturer #2
New Supporting A Lenel System (2) Started by Undisclosed Integrator #1	2	less than a minute by Michael Miller
Vast Difference In Pricing Of Access Control (6) Started by Sean Nelson	6	about 6 hours by Clint Hays
Looking For A Very Big Lens For IP Camera, Any Advice ? (8) Started by Decoux Guilhem	8	less than a minute by Decoux Guilhem

Discussion

Posts

Latest

Upcoming Mobile App Shootout - What Criteria Should Be Considered? (11)

Started by Sean Patton

about 1 hour by Undisclosed Manufacturer #4

Where Are The Pre/Post Motion Settings On Milestone? (6)

Started by Undisclosed Manufacturer #1

about 1 hour by Undisclosed Manufacturer #2

New

Supporting A Lenel System (2)

Started by Undisclosed Integrator #1