Hit enter to search or ESC to close
Self-Driving

Testing the Edge: The ‘Puppy Rover’ Helps Make Self-Driving Cars Safe for Dogs

This is the latest in our “Testing the Edge” series, focusing on ingenious ways that the Structured Test team at Argo AI tests different components, systems, and scenarios for self-driving cars. 

As autonomous vehicles make their way to more places around the world, one big key to earning trust among communities will be demonstrating they can coexist safely with other vehicles, pedestrians, cyclists, and our proverbial “best friends” on four legs — dogs. 

Because dogs can be small, low to the ground, move quickly, and don’t follow traffic signals or signs, it’s more difficult for both human drivers and autonomous vehicle sensors alike to spot them on the road. A 2008 study prepared for the U.S. Congress by the Western Transportation Institute of Montana State University, estimated that each year there are between one and two million incidents involving vehicles and animals of all species in the United States.

Self-driving technology company Argo AI is working hard to ensure dogs are kept safe in part with a clever, custom-built solution: a “puppy rover,” essentially a small, wheeled robot with a stuffed dog mounted on top. The rover rides around the company’s test track near Pittsburgh, Pennsylvania, and simulates a real-life dog running across the street in front of Argo’s test vehicles. 

Argo’s puppy rover was designed and built earlier this summer by Jack Work, a 35-year-old Integration Technician Associate working at the test track – a closed course where Argo evaluates how software and hardware updates to its self-driving system perform before deploying them to its wider fleet of test vehicles on public roads. 

“It’s made up of aluminum with a bunch of after-market parts,” Work says of Argo’s puppy rover. The rover’s base is that of a heavily modified radio-controlled car from the popular brand Traxxas, to which Work attached metal plates underneath and overhead using welding experience he gained at New Castle School of Trades. 

Using the rover’s remote control, engineers can drive it into the path of Argo’s self-driving cars on the test track, making sure that the cars’ suite of multiple overlapping sensors — stereo cameras, radar, and lidar — can “see” the pooch and stop, or navigate around it safely. Argo Lidar, a new custom-built sensor for Argo’s self-driving system, is specifically designed to detect small objects that other lidar technology may miss. 

By testing Argo’s self-driving system with the puppy rover, engineers can measure how long the system takes to detect the simulated dog, and how fast it is able to maneuver safely around it, or brake. From this data, they can then make updates to the system’s software to improve its detection accuracy, reaction time, motion forecasting, and decision-making. 

Another odd advantage the puppy rover has over its real-life counterparts: the stuffed dog can be easily swapped out, so Argo engineers can change its appearance and size on a dime, even switch species of animal entirely. This helps test the self-driving system on a wider range of small animal types.

“We also have a chihuahua and a cat,” Work says. 

Right now, the puppy rover is fitted with a stuffed pug to look like Work’s own dog, Wilbur, which he calls “Goob.” In honor of his loyal pooch, he’s personally taken to calling the puppy rover “Goob 2.” 

The entire project took Work – a native of Beaver County, Pennsylvania, who’s been with Argo for nearly three years – about two weeks to complete. He began working on the invention at the request of another colleague on Argo’s Structured Test team – a group that designs and builds a variety of innovative machines used to stage scenarios for Argo’s self-driving cars to navigate. 

From mud cannons to rain machines, these devices help Argo engineers see how the company’s self-driving system performs when exposed to real-world challenges and edge cases of the road, such as a dog running loose from its leash, or animals that are even tougher to detect. 

“We plan on creating smaller and smaller creatures to simulate,” Work explains. 

As a dog owner and animal lover, Work is personally motivated to help ensure the safety of any living thing that encounters Argo’s self-driving system.

Choose your lane

How Autonomous Vehicles Distinguish Between Bicycles and People Who Ride Them
Self-Driving

How Autonomous Vehicles Distinguish Between Bikes and People

When it comes to how autonomous vehicles see the world, humans come first, literally. Autonomous vehicles (AVs), like the kind operated by Pittsburgh-based Argo AI, use Machine Learning to detect and classify the objects in their surroundings, identifying people...
Why The League of American Bicyclists is optimistic about autonomous vehicles
Self-Driving

Why a Leading Cycling Advocacy Group Is Optimistic About Autonomous Vehicles

As autonomous vehicle use grows, AV companies and the League of American Bicyclists are collaborating on how to ensure cyclists and motorists can share the roads safely, even if the “motorist” is artificial intelligence software. As part of the...
Opinion

Self-Driving Is Arriving Right On Time. Just Like Ice Cream Did

Seven years ago, I was a self-driving skeptic. Not of the technology. Of all the “experts” promising autonomous vehicles would be everywhere by 2020. You didn’t need to be Nostradamus to know that was ridiculous. All you needed was...
Illustration of a futuristic parking deck turned into a mixed-use space, with AVs driving by
Business

How Autonomous Vehicles Could Help Transform Parking Lots

Researchers say it’s likely that autonomous vehicles (AVs) can help reduce the need for parking lots, opening more room for grass and trees and other elements of nature. It may not seem like it when you’re circling the block...
An illustration of an Argo autonomous vehicle in teal against a backdrop of buildings, a bicyclist, and research papers
Self-Driving

7 Big Breakthroughs From Argo Research at CVPR 2022

The 2022 Conference on Computer Vision and Pattern Recognition (CVPR 2022) is nearly here. Thousands of computer scientists, software engineers, and researchers from around the globe will gather in New Orleans to review and discuss their latest work in...
Self-Driving

Researchers Predict the Future With Lidar Data

Researchers at Carnegie Mellon University’s Argo AI Center for Autonomous Vehicle Research, a private-public partnership funded by Argo for advancing the autonomous-vehicle (AV) field, say they have come up with a way to use lidar data to visualize not...

Must Reads