Connect with us

Technology

Helm.ai Announces DNN Foundation Models for Intent Prediction and Path Planning

Published

11 months ago

on

Company Applies Deep Teaching to Build Scalable AI Approach for L2/L3 ADAS through L4

REDWOOD CITY, Calif., Dec. 27, 2023 /PRNewswire/ — Helm.ai, provider of next-generation AI software for autonomous driving and automation of robotics, today announced DNN (Deep Neural Network)-based foundation models for behavioral prediction and decision-making as part of the company’s AI software stack for high-end ADAS L2/L3 and L4 autonomous driving.  

The company has trained DNN foundation models to make predictions about the behavior of vehicles and pedestrians in complex urban scenarios, as well as to predict the path an autonomous vehicle would take in those situations, which are critical ingredients of the decision-making capabilities for self-driving cars. Helm.ai leveraged its industry-validated surround view full scene semantic segmentation and 3D detection system as the core representation to enable training intent prediction and path planning capabilities. Additionally, the foundation models are trained using the company’s proprietary Deep Teaching technology to achieve broad predictive capability in a scalable way.

Helm.ai’s technology learns directly from real driving data and uses the company’s highly accurate and temporally stable perception system to capture information about complex behaviors of vehicles and pedestrians and the surrounding driving environment, leading to DNNs that automatically learn subtle yet important aspects of urban driving. The foundation models powering Helm.ai’s intent and path prediction gather input from a series of observed images and generate predicted video sequences that represent the most likely possible outcomes of what happens next. The models also provide a predicted path for the autonomous vehicle that is consistent with the intent prediction. Both the intent prediction and path prediction capabilities are essential for planning the safest optimal action by the autonomous vehicle.

Importantly, the Helm DNN foundation models for intent prediction and path planning are trained in the highly scalable Deep Teaching paradigm, enabling unsupervised learning about complex urban driving scenarios directly from real driving data. This approach circumvents cumbersome physics-based simulators and hand-coded rules, which are insufficient to capture the full complexity of driving in the real world. In particular, the Helm.ai development and validation pipeline, while optimized for high end ADAS L2/L3 mass production software, can also be directly applied to L4 fully autonomous applications. Moreover, the Helm.ai scalable AI approach readily generalizes to robotics domains beyond self-driving vehicles.

Helm.ai is building an AI-first approach to autonomous driving that is designed to seamlessly scale from high-end ADAS L2/L3 mass production programs all the way to large scale L4 deployments. The company’s software-only platform is hardware-agnostic and vision-first, addressing the critical perception problem for vision yet also incorporating sensor fusion between vision and radar/lidar as needed. The technology advancements announced today accelerate the value of Helm.ai’s software offering by paving the way for scalable development and validation of AI-based intent prediction and path planning software for autonomous vehicles.

“At Helm.ai we are pioneering a highly scalable AI approach that addresses high end ADAS L2/L3 mass production and large scale L4 deployments simultaneously in the same framework,” said Helm.ai CEO Vladislav Voroninski.

“Perception is the critical first component of any self-driving stack. The more comprehensive and temporally stable a perception system is, the easier it is to build the downstream prediction capabilities, which is especially critical for complex urban environments. Leveraging our industry-validated surround-view urban perception system and Deep Teaching training technology, we trained DNN foundation models for intent prediction and path planning to learn directly from real driving data, allowing them to understand a wide variety of urban driving scenarios and the subtleties of human behavior without the need for traditional physics based simulators or hand-coded rules.”

Helm.ai closed a $55 million Series C funding round in August 2023. The round was led by Freeman Group and includes investments from venture capital firms ACVC Partners and Amplo as well as strategic investments from Honda Motor, Goodyear Ventures, and Sungwoo Hitech. This financing brings the total amount raised by Helm.ai to $102M.

About Helm.ai
Helm.ai is building the next generation of AI software for high-end ADAS, L4 autonomous driving and robotics. Founded in November 2016 in Menlo Park, CA, the company has re-envisioned the way AI software is built to make truly scalable autonomous driving a reality. For more information on Helm.ai, including its products, SDK and open career opportunities, visit https://www.helm.ai/ or find Helm.ai on LinkedIn.

Photo – https://mma.prnewswire.com/media/2307805/Intent___Path_Prediction_Top_3.mp4
Logo – https://mma.prnewswire.com/media/1178129/Helm_ai_logo.jpg 

View original content:https://www.prnewswire.co.uk/news-releases/helmai-announces-dnn-foundation-models-for-intent-prediction-and-path-planning-302022560.html

Related Topics:
Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Technology

Gentoo Media – Mandatory notification of trade

Published

32 minutes ago

on

November 14, 2024

By

ST JULIANS, Malta, Nov. 14, 2024 /PRNewswire/ — MJ Foundation Fundacja Rodzinna, a company related to Mateusz Juroszek, Board Member and primary insider of Gentoo Media Inc. (Gentoo) has today acquired 115,604 shares in Gentoo at a price of SEK 24,996 per share. After this transaction, close associates of Mateusz Juroszek hold 24,027,766 shares in Gentoo.

This information is subject to the disclosure requirements pursuant to Section 5-12 of the Norwegian Securities Trading Act.

For further information, contact:
Tore Formo, Group CFO, tore.formo@g2m.com, +47 91668678

About Gentoo Media

Gentoo Media is a market-leading affiliate connecting operators and players in the online gambling and sports betting industry. Gentoo Media offers an array of iGaming affiliate solutions, such as paid marketing expertise and quality traffic through our prominent industry sites including AskGamblers, Time2Play, CasinoTopsOnline, WSN and Casinomeister. In 2024, Gentoo Media (formerly GiG Media) became Gentoo Media Inc. following a legal split separating the Media and Platform and Sportsbook business in Gaming Innovation Group (GiG) into two independently listed companies. Gentoo Media Inc. is dual listed on the Oslo Stock Exchange (ticker “G2MNO”) and Nasdaq Stockholm (ticker “G2M”). www.gentoomedia.com

This information was brought to you by Cision http://news.cision.com

https://news.cision.com/gentoo-media-inc/r/gentoo-media—mandatory-notification-of-trade,c4066199

View original content:https://www.prnewswire.co.uk/news-releases/gentoo-media—mandatory-notification-of-trade-302305030.html

Continue Reading

Technology

Xinhua Silk Road: World IoT expo 2024 opens in E. China’s Wuxi to showcase future of smart connectivity

Published

32 minutes ago

on

November 14, 2024

By

BEIJING, Nov. 14, 2024 /PRNewswire/ — The World Internet of Things (IoT) Exposition 2024 kicked off on Monday in Wuxi City of east China’s Jiangsu Province, attracting industry leaders, representatives of enterprises and experts from across the globe to discuss industry trends and demonstrate innovative applications.

At the expo’s opening ceremony, Wuxi unveiled a national pilot project in intelligent connected vehicles, which aims to create a cohesive mode for car owners, vehicles and cities connection, contributing Wuxi’s expertise to smart vehicle initiatives.

Additionally, a new smart sensing chip engineering center was launched, representing an investment of over 1 billion yuan and focusing on high-density large-scale substrates and other advanced chip technologies to strengthen the city’s integrated circuit development.

The event also saw the release of several major IoT research achievements, including the 2024 IoT innovation development Taihu index and the 2024 white paper on advanced sensing technology and applications.

The three-day event features exhibitions, panel discussions, and thematic sessions that showcase the latest development in IoT innovations and applications. This year’s expo is poised to drive Wuxi’s high-quality growth in IoT while promoting global tech collaboration and knowledge sharing in the IoT field.

Wuxi has become a navigator of the IoT industry in China. The latest statistics show that in 2023, the scale of the IoT industrial cluster in Wuxi surpassed 450 billion yuan, taking the lead in Jiangsu Province.

Original link: https://en.imsilkroad.com/p/343117.html

SOURCE Xinhua Silk Road

Continue Reading

Technology

Agoda Highlights Five Urban Hikes for Adventurous Travelers

Published

32 minutes ago

on

November 14, 2024

By

SINGAPORE, Nov. 14, 2024 /PRNewswire/ — Digital travel platform Agoda introduces five urban hikes across Asia, offering travelers a chance to experience the perfect blend of city life and nature. These hikes, ranging from family-friendly to more challenging trails, provide an unmatched perspective on some of Asia’s most dynamic cities.

Whether it’s Elephant Hill in Taipei, with its stunning views of the Taipei 101, or Hong Kong’s famous Dragon Back, active travelers are in for a treat when embarking on these city hike adventures.

Andrew Smith, Senior Vice President, Supply at Agoda said: “Asia is special to have so many incredible hike routes right in the heart of these popular cities. The five highlighted hikes are just a sample of the many breathtaking city trails the continent has to offer. Adventurous travelers will want to try them all and thankfully Agoda helps make travel affordable with great value deals on over 4.5 million properties globally.”

These are the five city hikes, ranked from easiest to most challenging:

Kuala Lumpur’s Bukit Nanas Forest Reserve offers a unique experience of trekking through a tropical rainforest right in the city center. The trail is relatively easy, with well-marked paths and informative signboards about the local flora and fauna, making it a great choice for families and nature enthusiasts.

Elephant Hill in Taipei offers a short but rewarding climb. The trail is well-maintained and provides stunning views of Taipei’s skyline, including the famous Taipei 101. It’s an ideal spot for those looking to enjoy a quick escape into nature without straying far from the city.

In Singapore, the Southern Ridges trail offers a moderate hike through a series of interconnected parks and gardens. Spanning 10 kilometers, this trail provides a lush green corridor amidst the urban environment, with highlights including the Henderson Waves bridge and panoramic views of the city.

Namsan in Seoul presents a slightly more challenging hike, leading to the N Seoul Tower. The trail is popular among locals and tourists alike, offering a mix of natural beauty and cultural landmarks, with several routes to choose from depending on the desired difficulty level.

Finally, Hong Kong’s Dragon’s Back is a favorite for its breathtaking views of the coastline and the South China Sea. This moderately challenging hike is known for its undulating ridges and scenic vistas, providing a rewarding experience for those willing to tackle its ups and downs.

In each of these city hike destinations, Agoda offers great value accommodation. In addition to holiday properties, Agoda’s 130,000 flight routes and 300,000 activities ensure the platform is the one-stop travel solution to help booking an entire trip. The latest Agoda deals can be found in the Agoda app or on agoda.com/deals.

— ENDS —

 

View original content to download multimedia:https://www.prnewswire.com/apac/news-releases/agoda-highlights-five-urban-hikes-for-adventurous-travelers-302304670.html

SOURCE Agoda

Continue Reading

Trending