Fully autonomous vehicles seem to perennially be just a few years away, sort of like the automotive equivalent of fusion power. But just because robotic vehicles haven’t made much progress on our roadways doesn’t mean we can’t play with the technology at the hobbyist level. You can embark on your own experimentation right now with this open source self-driving Python library.
Granted, this is a library built for much smaller vehicles, but it’s still quite full-featured. Known as Donkey Car, it’s mostly intended for what would otherwise be remote-controlled cars or robotics platforms. The library is built to be as minimalist as possible with modularity as a design principle, and includes the ability to self-drive with computer vision using machine-learning algorithms. It is capable of logging sensor data and interfacing with various controllers as well, either physical devices or through something like a browser.
To build a complete platform costs around $250 in parts, but most things needed for a Donkey Car compatible build are easily sourced and it won’t be too long before your own RC vehicle has more “full self-driving” capabilities than a Tesla, and potentially less risk of having a major security vulnerability as well.
Well, we guess it had to happen eventually — Ford is putting plans in place to make its vehicles capable of self-repossession. At least it seems so from a patent application that was published last week, which reads like something written by someone who fancies themselves an evil genius but is just really, really annoying. Like most patent applications, it covers a lot of ground; aside from the obvious capability of a self-driving car to drive itself back to the dealership, Ford lists a number of steps that its proposed system could take before or instead of driving the car away from someone who’s behind on payments.
Examples include selective disabling conveniences in the vehicle, like the HVAC or infotainment systems, or even locking the doors and effectively bricking the vehicle. Ford graciously makes allowance for using the repossessed vehicle in an emergency, and makes mention of using cameras in the vehicle and a “neural network” to verify that the locked-out user is indeed having, say, a medical emergency. What could possibly go wrong?
Continue reading “Hackaday Links: March 5, 2023” →
Scotland! It’s the land of tartans, haggis, and surprisingly-warm kilts. It’s also ground zero for the first trial of full-sized driverless buses in the United Kingdom.
It’s not just automakers developing driverless technologies. Transit companies are desperate to get in on the action because it would completely upend their entire existing business structure. Now that self-driving buses are finally approaching a basic level of competence, they’re starting to head out to haul passengers from A to B. Let’s look at how the UK’s first driverless bus project is getting on out in the real world.
Continue reading “Driverless Buses Take To The Road In Scotland” →
For as popular as they became during the COVID-19 lockdowns, grocery delivery services like InstaCart rely on a basic assumption to work: that customers know exactly what they want when they order. Once that hurdle is overcome, the transaction is simple — the driver accepts the job, drives to the store to pick up the order, and takes it to the customer. It requires the use of a fair amount of technology to coordinate everything, but by and large it works, and customers are generally willing to pay for the convenience.
But what if you could cut out that step where the driver goes to pick up your order? What if instead of paying someone to pick and pack your order and bring it to your front step, you just ordered up the whole store instead? That’s the idea behind Robomart, which seeks to deploy a fleet of mobile stores for when the convenience store isn’t quite convenient enough. And the way the company is choosing to roll out its service, not to mention the business model itself, may hold key lessons for other delivery automation platforms.
Continue reading “Automate The Freight: The Convenience Store That Comes To Your Door” →
We write a lot about self-driving vehicles here at Hackaday, but it’s fair to say that most of the limelight has fallen upon large and well-known technology companies on the west coast of the USA. It’s worth drawing attention to other parts of the world where just as much research has gone into autonomous transport, and on that note there’s an interesting milestone from Europe. The British company Oxbotica has successfully made the first zero-occupancy on-road journey in Europe, on a public road in Oxford, UK.
The glossy promo video below the break shows the feat as the vehicle with number plates signifying its on-road legality drives round the relatively quiet roads through one of the city’s technology parks, and promises a bright future of local deliveries and urban transport. The vehicle itself is interesting, it’s a platform supplied by the Aussie outfit AppliedEV, an electric spaceframe vehicle that’s designed to provide a versatile platform for autonomous transport. As such, unlike so many of the aforementioned high-profile vehicles, it has no passenger cabin and no on-board driver to take the wheel in a calamity; instead it’s driven by Oxbotica’s technology and has their sensor pylon attached to its centre.
Continue reading “European Roads See First Zero-Occupancy Autonomous Journey” →
Bluster around the advent of self-driving cars has become a constant in the automotive world in recent years. Much is promised by all comers, but real-world results – and customer-ready technologies – remain scarce on the street.
Today, we’ll dive in and take a look at the current state of play. What makes a self-driving car, how close are the main players, and what can we expect to come around the corner?
Continue reading “The Current State Of Play In Autonomous Cars” →
The US National Highway Traffic Safety Administration (NHTSA) has opened a formal investigation about Tesla’s automatic driving features (PDF), claiming to have identified 11 accidents that are of concern. In particular, they are looking at the feature Tesla calls “Autopilot” or traffic-aware cruise control” while approaching stopped responder vehicles like fire trucks or ambulances. According to the statement from NHTSA, most of the cases were at night and also involved warning devices such as cones, flashing lights, or a sign with an arrow that, you would presume, would have made a human driver cautious.
There are no details about the severity of those accidents. In the events being studied, the NHTSA reports that vehicles using the traffic-aware cruise control “encountered first responder scenes and subsequently struck one or more vehicles involved with those scenes.”
Despite how they have marketed the features, Tesla will tell you that none of their vehicles are truly self-driving and that the driver must maintain control. That’s assuming a lot, even if you ignore the fact that some Tesla owners have gone to great lengths to bypass the need to have a driver in control. Tesla has promised full automation for driving and is testing that feature, but as of the time of writing the company still indicates active driver supervision is necessary when using existing “Full Self-Driving” features.
We’ve talked a lot about self-driving car safety in the past. We’ve also covered some of the more public accidents we’ve heard about. What do you think? Are self-driving cars as close to reality as they’d like you to believe? Let us know what you think in the comments.