Skip to main content

Best viewed in portrait mode

Blog Post


Why We Do AV Software Recalls

One of our Cruise AVs was recently involved in a minor collision after a city bus slowed and the AV was late to brake behind it. It resulted in minor damage to the front fender of the AV and caused no injuries.  

Fender benders like this rarely happen to our AVs, but this incident was unique. We do not expect our vehicles to run into the back of a city bus under any conditions, so even a single incident like this was worthy of immediate and careful study.

I want to walk you through our investigation of the incident, what we’ve done to address our findings, and why we ultimately chose to file a voluntary recall with the National Highway Transportation Safety Administration (NHTSA). These actions are a reflection of the rigorous safety culture that we’ve built at Cruise and our deep commitment to improving roadway safety. 

What Happened

Less than an hour after the collision, we had fully assembled a team to investigate what happened. We also moved quickly to brief our state and federal regulators on the incident and made our team available to answer any questions they had.

We quickly determined the bus’s behavior was reasonable and predictable. It pulled out into a lane of traffic from a bus stop and then came to a stop. Although our car did brake in response, it applied the brakes too late and rear-ended the bus at about 10 mph. We identified the root cause, which was a unique error related to predicting the movement of articulated vehicles (i.e. vehicles with two sections connected by a flexible joint, allowing them to bend in the middle) like the bus involved in this incident.

In this case, the AV's view of the bus’s front section became fully blocked as the bus pulled out in front of the AV. Since the AV had previously seen the front section and recognized that the bus could bend, it predicted that the bus would move as connected sections with the rear section following the predicted path of the front section. This caused an error where the AV reacted based on the predicted actions of the front end of the bus (which it could no longer see), rather than the actual actions of the rear section of the bus. That is why the AV was slow to brake.

What We Did

Once we understood the root cause, our engineering teams immediately started creating a software update that would significantly improve performance near articulated vehicles. Once that work was completed, tested, and validated, our operations team rolled the change out to the fleet. This work was completed within two days of the incident occurring. The results from our testing indicated that this specific issue would not recur after the update.

Although we resolved the root cause in this particular incident, our teams continued to investigate the full extent to which this kind of issue occurred in the past, might occur under a variety of conditions in the future, and might be identified sooner. Our vehicles encounter buses like this one every day, but we’d never caused this kind of collision before. We needed to understand if it was more widespread or isolated to a very unique and rare set of initial conditions.

Our data and simulations showed that it was exceptionally rare. At the time of the incident, our AVs had driven over 1 million miles in fully driverless mode. We had no other collisions related to this issue, and extensive simulation showed that similar incidents were extremely unlikely to occur at all, even under very similar conditions. The collision occurred due to a unique combination of specific parameters such as the specific position of the vehicles when the AV approached the bus (with both sections of the bus visible initially, and then only one section), the AV’s speed, and the timing of the bus’s deceleration (within only a few seconds of the front section becoming occluded).

Although we determined that the issue was rare, we felt the performance of this version of software in this situation was not good enough. We took the proactive step of notifying NHTSA that we would be filing a voluntary recall of previous versions of our software that were impacted by the issue.

Looking Ahead

The process we followed in this case is just one example of our commitment to safety and our ability to rapidly diagnose, react to, and remedy any issues we may encounter.

We will undoubtedly continue to discover ways in which we can improve, even if that involves changing software that is currently deployed in the field. We think any potential improvement to roadway safety is worthwhile, and we will approach it with the same level of rigor as we’ve demonstrated here. These continuous improvements are likely to make voluntary recalls commonplace. We believe this is one of the great benefits of autonomous vehicles compared to human drivers; our entire fleet of AVs is able to rapidly improve, and we are able to carefully monitor that progress over time.

I appreciate the opportunity to provide some additional insight into how we approach our work. We’re lucky to have a strong relationship with NHTSA and other regulators and to have partners so dedicated to road safety. We will continue to work together and with urgency to put an end to the tragic status quo on our roads today.