Synkrotron
Founded in 2019, Synkrotron offers products and solutions for the data-driven development of autonomous driving and intelligent traffic technologies. The company’s main product offering includes vehicle data acquisition system Oasis Rover, autonomous driving data platform Oasis Data and simulation platform Oasis Sim.
Value Proposition
Synkrotron developed the SYNKROTRON® OASIS product suite by taking advantages of several technologies such as software verification and validation (V&V), physics simulation, digital twin, deep learning and big data, etc. OASIS is equipped with high-precision sensor models, vehicle dynamics models, multi-agent interaction models, SOTIF-based scenario generation and reconstruction capabilities. The goal of OASIS is to accelerate the large-scale training, development and V&V of Autonomous Driving Systems (ADS). By carrying out such R&D activities on a simulation-centric platform, customers such as Autoware developers can identify ADS defects in advance, reduce the cost of real-world testing and eliminate the safety hazards inherited in the current process.
Technology Description
Synkrotron provides advanced solutions for autonomous driving simulation built on top of CARLA. Synkrotron’s product suite OASIS supports a broad range of applications including scenario generation, sensor modelling, traffic simulation and data management. Based on a flexible architecture OASIS can be deployed on the cloud at scale, or in a developer’s local environment for prototyping.
Oasis SimOasis Sim is a fully-fledged scalable simulation platform with CARLA at its core. It supports the complete life cycle of AD simulation:
Scenario Import and Editing
Oasis Sim comes with a Scenario Editor which enables users to design and edit traffic scenarios. Users can specify the environment condition, the driving task of the ego vehicle and the behaviors of other traffic participants. The definition of these elements is compatible with OpenScenario 1.0 and can be imported from external sources or exported. On top of these, users can also add a background traffic flow to interact with the ego vehicle as well as the traffic participants whose behaviors are already defined by the user. Traffic flow adds diversity to the scenario and makes it more consistent with a real driving environment.
Vehicle Configuration
In the Vehicle Configuration panel users can equip the ego vehicle with pre-defined sensor types, a vehicle dynamics model and an autonomous driving system. This panel offers visualization of sensor placements and FOVs.
Distributed task management
A simulation task is formed by associating an existing ego vehicle with a scenario, both of which are already defined in the Vehicle Configuration panel and the Scenario Editor, respectively. A simulation job is a container of multiple simulation tasks. Once a simulation job is created it can then be run in parallel on multiple Oasis worker nodes behind the scenes. Each worker runs a portion of the list of tasks.
Diagnosis
Once a task is finished users will be able to access the details of the simulation results via the Diagnosis panel. This panel contains rich information about the details of the simulation, including sensor data playbacks, spectator views, system logs as well as the results of various evaluation criteria. This is intended to help users with trouble-shooting their autonomous system under test.
Deployment and Integration
Both cloud and local deployments of Oasis Sim are available through containers. Comprehensive APIs are exposed for integration with DevOps as well. You can request a trial from Synkrotron.
Oasis Data Oasis Data is a platform for managing the high volume of data flowing through the autonomous driving R&D pipeline. Data-driven development of AD systems is made possible with Oasis Data via the following functionalities,data acquisition and anonymizationmulti-stage filtering based on structured (CAN bus signals, active-safety triggering, etc.) and unstructured (sensor readings) information.mapping and environment reconstruction with lidar and/or vision-only strategy.auto-labeling of data with pre-trained perception models.scenario tagging and reconstruction with OpenX format output.The processed data from the platform supports downstream applications such as scenario re-simulation with Oasis Sim, retraining of perception models with new labeled data and operational fleet management.
Oasis Rover
Oasis Rover is an All in One Multi-sensor data acquisition and data injection system. It provides synchronized sensor data recording of today’s and tomorrow’s intelligent vehicle. Oasis Rover also allows for data playback and injecting simulated data in both open and closed-loop testing environments.