Abstract: Embodiments of the disclosed systems and methods provide for determination of roadway traversability by an autonomous vehicle using real time data and a trained traversability determination machine learning model. Consistent with aspects of the disclosed embodiments, the model may be trained using annotated birds eye view perspective data obtained using vehicle vision sensor systems (e.g., LiDAR and/or camera systems). During operation of a vehicle, vision sensor data may be used to construct birds eye view perspective data, which may be provided to the trained model. The model may label and/or otherwise annotate the vision sensor data based on relationships identified in the model training process to identify associated road boundary and/or lane information. Local vehicle control systems may compute control actions and issue commands to associated vehicle control systems to ensure the vehicle travels within a desired path.
Type:
Application
Filed:
July 22, 2022
Publication date:
February 16, 2023
Applicant:
Sensible 4 Oy
Inventors:
Miika Lehtimäki, Jari Saarinen, Ashish Khatke, Enes Özipek, Teemu Kuusisto, Hamza Hanchi
Abstract: Embodiments of the disclosed systems and methods provide for systems and methods for collecting and managing vehicle and infrastructure sensor measurement data and building predictive models based on such data. In certain embodiments, operation and/or control of a vehicle may be based on the predictive model. In certain embodiments, the predictive model may be generated and/or otherwise trained based on actual vehicle measurement data and actual infrastructure measurement data that has been correlated by associated time and/or location. In further embodiments, model validation techniques may be used to determine a predictive quality of the model.
Abstract: Embodiments of the disclosed systems and methods provide techniques for dynamically allocating processing tasks between in-vehicle and remote processing resources. In various embodiments, aspects of the disclosed systems and methods may advantageously use relatively low latency edge cloud and/or cloud processing resources accessed via higher speed wireless networks to enhance processing resources available to a vehicle for use in a variety of control and/or operation decisions. Consistent with various disclosed embodiments, processing tasks may be dynamically allocated based on relative impact and/or importance to safe vehicle operation, network latency between a vehicle and remote processing resources, available network bandwidth between a vehicle and remote processing resources, network traffic, processing complexity, processing resource availability, and/or the like.
Abstract: Embodiments of the disclosed systems and methods provide systems and techniques for improving reference route and/or trajectory information for autonomous vehicles that may allow for better operation and/or deployment. In certain embodiments, various optimization techniques may be employed for generating higher quality reference route and/or trajectory information based on initial reference route and/or trajectory information captured by an autonomous vehicle. Various embodiments of the disclosed systems and methods may improve reference route and/or trajectory information through processes that may involve editing and/or otherwise modifying initial route and/or trajectory information, smoothing path curves associated with initial reference route and/or trajectory information, modifying initial route and/or trajectory information based on vehicle-specific dynamics and/or parameters, and/or modifying velocities for improved passenger comfort.
Type:
Application
Filed:
November 23, 2021
Publication date:
May 26, 2022
Applicant:
Sensible 4 Oy
Inventors:
Gábor Major, Umar Zakir Abdul Hamid, Jari Saarinen, Aku Kyyhkynen