Automakers and tech developers testing and deploying self-driving and advanced driver assistance features will no longer have to report as much detailed, public crash information to the federal government, according to a new framework released today by the US Department of Transportation. The moves are a boon for makers of self-driving cars and the wider vehicle technology industry, which has complained that federal crash reporting requirements are overly burdensome and redundant. But the new rules will limit the information available to those who watchdog and study autonomous vehicles and driver assistance features--tech developments that are deeply entwined with public safety but which companies often shield from public view because they involve proprietary systems that companies spend billions to develop. The government's new orders limit "one of the only sources of publicly available data that we have on incidents involving Level 2 systems," says Sam Abuelsamid, who writes about the self-driving vehicle industry and is the vice president of marketing at Telemetry, a Michigan research firm, referring to driver assistance features such as Tesla's Full Self-Driving (Supervised), General Motors' Super Cruise, and Ford's Blue Cruise. These incidents, he notes, are only becoming "more common."

Unsignalized intersections are typically considered as one of the most representative and challenging scenarios for self-driving vehicles. To tackle autonomous driving problems in such scenarios, this paper proposes a curriculum proximal policy optimization (CPPO) framework with stage-decaying clipping. By adjusting the clipping parameter during different stages of training through proximal policy optimization (PPO), the vehicle can first rapidly search for an approximate optimal policy or its neighborhood with a large parameter, and then converges to the optimal policy with a small one. Particularly, the stage-based curriculum learning technology is incorporated into the proposed framework to improve the generalization performance and further accelerate the training process. Moreover, the reward function is specially designed in view of different curriculum settings. A series of comparative experiments are conducted in intersection-crossing scenarios with bi-lane carriageways to verify the effectiveness of the proposed CPPO method. The results show that the proposed approach demonstrates better adaptiveness to different dynamic and complex environments, as well as faster training speed over baseline methods.

There's a whole genre of YouTube videos of people showing how their Teslas can drive themselves around. These users are testing out Tesla's Full Self-Driving capabilities--which sometimes work great, and other times … not so much. Most of these videos are made by true believers who want the company to succeed but are also honest when the tech fails and Tesla's promises fall short. These promises, after all, are big--and have long come directly from Elon Musk. But so are the risks: Last month, Tesla recalled around 360,000 cars with the company's Full Self-Driving beta system--which, in this case, meant the company had to push a software update to address behavior that increased the risk of a crash, like exceeding speed limits or traveling through intersections, according to a government regulator.

This article is sponsored by Oracle – redefining data management with the world's first autonomous database. In the coming years, the amount of data we create worldwide will grow to 175 zettabytes of data per year by 2025, up from 33 zettabytes in 2018. Over half of this data will be created by the Internet of Things devices and over 60% of it will be enterprise data. By 2025, 30% of all the data created will be in real-time, offering organisations great opportunities to constantly optimise their business. Clearly, the organisation of tomorrow is a data organisation.

The National Highway Traffic Safety Administration has released its first batch of data for semi-autonomous driving technology. As The New York Times explains, the agency linked 392 crashes to self-driving and driver assistance systems in the 10 months between July 1st, 2021 and May 15th, 2022. About 70 percent of those, 273, were Tesla vehicles using Autopilot or the Full Self-Driving beta. Honda cars were tied to 90 incidents, while Subaru models were involved in 10. Other makes, including Ford, GM, VW and Toyota, had five incidents or less.

At a blistering top speed of 0.1 miles per hour, Perseverance is shattering what scientists thought possible from a Mars rover. Well, I'll remind you that it's doing this on a whole other goddamn planet, often by itself. A vehicle 127 million miles away is making its own decisions on how to cross a treacherous and truly alien landscape all on its own, and it's doing it at an incredible (for a rover anyway) 300 yards-a-day pace. Normally, special operators use headsets and 3D monitors to help navigate the rover over the rocky Martian landscape, which is very cool and sci-fi on its own. But now that Perseverance has a bit of a stretch of travel ahead of it, NASA is letting the little guy make his own way in the world while putting the pedal to the metal.

AMSTERDAM, Oct 27 (Reuters) - Visitors to Amsterdam may soon spot a self-driving watercraft the size of a small car cruising silently through its ancient canals, ferrying passengers or transporting goods or trash. It will be the electric-powered "Roboat", a catchier name than "autonomous floating vehicle" for a project shortly due to start test journeys aimed at improving the crowded city's transport options. "We have a lot of road traffic and congestion, e-commerce, logistics cluttering the small streets in the city," said Stephan van Dijk, Innovation Director at Amsterdam's Institute for Advanced Metropolitan Solutions, which is designing and engineering Roboat with The Massachusetts Institute of Technology (MIT). "At the same time we have a lot of open water available in the canals ... So we developed a self-driving, autonomous ship to help with logistics in the city and also bringing people around." One of the first test applications of the craft will be for an unglamorous but important task: trash collection.

Argo tests in multiple cities to ensure its SDS is exposed to a wide range of driving regulations, enabling it to operate appropriately and consistently with local rules, which often vary from place to place. Consider, for example, how a vehicle should behave when turning right if there is a bike lane. In California, a car may occupy the bike lane to turn right on red, but in Pennsylvania, the same right turn requires the car to stay in the vehicle lane. Argo's powerful prediction system can incorporate a database of driving styles from which to match data, anticipate likely actions, make appropriate decisions, and avoid extreme situations in order to achieve "naturalistic driving." The SDS can even handle the (in)famous "Pittsburgh left," an unwritten rule in Argo's home city which calls for oncoming traffic to give up the right-of-way and politely let left-turning vehicles turn against a green.

The Society for Automotive Engineering (SAE) has identified five levels of self-driving which describe how much a particular vehicle is able to handle its own driving tasks. Level 1 means that the vehicle handles either the speed or the steering, but not both, and it requires supervision. While ordinary cruise control technically falls into this level, most people associate cruise control with adaptive cruise control, which slows down or speeds up with traffic. A Level 2 car can control the speed and the steering but the driver must still maintain full vigilance. At Level 3, the driver need not maintain total vigilance but must still be able to take control upon request.

Tesla may be in all of the electric headlines because of its bizarre price cuts on the Model S, but the automaker's CEO announced some big news in a tweet last week. Before we get into that, we should go back to where it started. During Tesla's annual Battery Day earlier this September, Musk claimed that a private beta test of the brand's Full Self-Driving suite would come out in the next few months. With October coming down to an end, it turns out that Tesla's ahead of schedule with its beta test. Limited Full Self Driving Testing Coming Soon In a recent tweet, Musk claimed that a limited release of the automaker's Full Self-Driving suite would be out on Tuesday, October 20.