Software that contains machine learning algorithms is an integral part of automotive perception, for example, in driving automation systems. The development of such software, specifically the training and validation of the machine learning components, require large annotated datasets. An industry of data and annotation services has emerged to serve the development of such data-intensive automotive software components. Wide-spread difficulties to specify data and annotation needs challenge collaborations between OEMs (Original Equipment Manufacturers) and their suppliers of software components, data, and annotations. This paper investigates the reasons for these difficulties for practitioners in the Swedish automotive industry to arrive at clear specifications for data and annotations. The results from an interview study show that a lack of effective metrics for data quality aspects, ambiguities in the way of working, unclear definitions of annotation quality, and deficits in the business ecosystems are causes for the difficulty in deriving the specifications. We provide a list of recommendations that can mitigate challenges when deriving specifications and we propose future research opportunities to overcome these challenges. Our work contributes towards the on-going research on accountability of machine learning as applied to complex software systems, especially for high-stake applications such as automated driving.

EOS partners with QUANERGY to distribute false alarm-reducing LiDAR technology for security applications in the ANZ market. Quanergy Systems is a provider of LiDAR sensors and Smart 3D Computer Perception Software – the brains of Quanergy's 3D AI-powered LiDAR FlowManagement platform, aimed at increasing efficiency in response to security breaches and reducing costly false alarms. "Quanergy's LiDAR is the pinnacle technology for perimeter intrusion detection," said EOS MD, Patrick Cha. "Quanergy's platform is designed to increase efficiency in response to security breaches and drastically reduce costly false alarms. "We are proud to be a partner of Quanergy and we look forward to distributing the LiDAR sensor and 3D perception software to the ANZ market to further enhance electronic security systems for perimeter and smart city projects."

IRVINE, Calif., Dec. 16, 2021 (GLOBE NEWSWIRE) -- Seoul Robotics, the 3D perception solution company using deep learning AI to power the future of mobility, today announced that in 2021 the company more than doubled the number of partnerships and global employees. In July alone, Seoul Robotics closed more business than in the entirety of 2020. Since launching in North America in January 2021, Seoul Robotics has introduced three plug-and-play 3D perception systems, Discovery, Voyage, and Endeavor, as well as the most advanced version of its 3D perception platform, SENSR 2.2. SENSR 2.2 is the only 3D perception software on the market leveraging deep learning AI and is compatible with over 75 different makes and models of 3D sensors, including LiDAR. Over the past year, Seoul Robotics has secured and scaled solutions with several top-tier companies and government entities, including multiple Tier-1 original equipment manufacturers (OEMs) and Departments of Transportation.

Data is the reason AV companies are racking up miles and miles of testing experience on public roads, recording and stockpiling petabytes of road lore. Waymo, for example, claimed in July more than 10 million miles in the real world and 10 billion miles in simulation. But here's yet another question the industry does not like to ask: Assume that AV companies have already collected petabytes or even exabytes of data on real roads. How much of that dataset has been labeled? Perhaps more important, how accurate is the data that's been annotated?

ANSYS (NASDAQ: ANSS) is collaborating with Edge Case Research to engineer the next generation of autonomous vehicles (AV) with unmatched state-of-the-art hazard detection capabilities. Through a new OEM agreement, Edge Case Research integrates its powerful AV artificial intelligence (AI) perception stress testing and risk analysis system, Hologram, within ANSYS' comprehensive AV simulation solution -- delivering a solution to maximize the safety of AVs. Today's AVs rely on AI perception algorithms that are trained to make safety-critical driving decisions. Though highly advanced, an AV may fail to detect hazardous driving scenarios known as "edge cases" -- because its algorithmic training has not prepared it for the many unusual road situations it will encounter in the real world. To ensure the highest safety of an AV -- and make fully autonomous vehicles a reality, developers need tools to automatically identify these challenging edge cases in a way that is far more scalable than manual data labeling.

Perception system design is a very critical step in the development of an autonomous vehicle (AV). To obtain human level perception, autonomous vehicles primarily use sensor technologies such as LiDARs, RADARs, and Cameras. Self-driving vehicles also need to be equipped with state-of-the-art AV perception technology. DeepScale is a leader in efficient deep learning perception software for use in mass-produced automated vehicles. Today, the company announced it has secured a $15 million Series A funding investment led by Point72 and next47.