Tag: autonomous vehicles

  • Russia Aims for 50% Driverless Vehicles by 2050, Trucks Active Now

    Russia Aims for 50% Driverless Vehicles by 2050, Trucks Active Now

    Key Takeaways

    1. The Russian Ministry of Transport aims for 50% of vehicles to be driverless by 2050.
    2. Approximately 90 driverless freight trucks are currently operating on national toll highways, covering over 6 million kilometers.
    3. Russia has launched fully autonomous freight vehicles on major routes, including the Central Ring Road in Moscow and the M-11 Neva highway.
    4. A recent unmanned truck completed a 1,600-kilometer journey, though engineers were present during the trip.
    5. Russia is updating laws and infrastructure to support Level 5 autonomy, with a federal law expected to be passed by 2026 and implemented by 2027.

    The Russian Ministry of Transport aims for 50% of all vehicles in the country to be driverless by 2050. This ambition was shared on Thursday by Deputy Transport Minister Vladimir Poteshkin, who mentioned that “work is currently underway to set up the necessary conditions for this.”

    Aiming for Full Autonomy

    This target is part of a wider initiative to create a completely self-driving transportation system. Poteshkin pointed out that around 90 driverless freight trucks are already working, moving goods on national toll highways. These trucks have collectively covered over 6 million kilometers to date.

    Recent Achievements in Autonomous Transport

    Russia has already achieved significant milestones in its quest for autonomous transportation. Back in April, the nation introduced a fleet of fully autonomous freight vehicles on the Central Ring Road in Moscow. Before this, a similar project had been functioning on the M-11 Neva highway since 2023. Furthermore, a recent unmanned truck successfully made a 1,600-kilometer trip from St. Petersburg to Kazan, although it had engineers in the cab during the journey.

    Regulatory Changes for Level 5 Autonomy

    To facilitate its aim for full Level 5 autonomy—where vehicles won’t need any drivers—Russia is modifying its laws and improving road infrastructure. Transport Minister Andrey Nikitin mentioned that there is a detailed plan for developing unmanned transport until 2028. A central element of this plan is a new federal law concerning highly automated vehicles, which officials hope to pass in 2026 and put into effect by the third quarter of 2027.

    Source:
    Link

     

    Tags:
  • New MvACon AI Enhances Self-Driving Car Perception Accuracy

    New MvACon AI Enhances Self-Driving Car Perception Accuracy

    Researchers at North Carolina State University have come up with a fresh method to assist self-driving cars in understanding their surroundings more effectively. This innovative system, called Multi-View Attentive Contextualization (MvACon), tackles some of the usual problems seen in existing vision transformer AI models that are designed to detect objects in 3D from various perspectives.

    Enhanced Detection Performance

    To evaluate its effectiveness, the team conducted multiple experiments using the nuScenes dataset, which is well-known in the realm of autonomous driving. MvACon significantly improved detection accuracy across different leading vision systems. When integrated with the BEVFormer system, it demonstrated noticeable advancements in identifying object locations, predicting their orientations, and estimating their speeds.

    Local Object-Context Awareness

    The researchers discovered that the attention mechanism of MvACon, which concentrates on clusters, keeps the detection precise for both vehicles and surrounding structures. They refer to this as a "local object-context aware coordinate system," suggesting that the system gains an enhanced understanding of spatial relationships, which is crucial for effectively tracking movement and orientation.

    Compatibility and Versatility

    A standout feature of this technology is its ease of integration into existing autonomous vehicle vision systems without requiring additional hardware. Regardless of the configuration, it consistently enhances performance, making it a versatile tool for various implementations.

    Testing results indicate that the system operates well even in complex situations with numerous overlapping objects.

    Tags: