Dataset of over 33 hours of commute in California’s 280 highway. This means 2019 segments, 1 minute long each, on a 20km section of highway driving between California’s San Jose and San Francisco. The dataset was collected using comma EONs that have sensors similar to those of any modern smartphone including a road-facing camera, phone GPS, thermometers and a 9-axis IMU. Additionally, the EON captures raw GNSS measurements and all CAN data sent by the car with a comma grey panda. Laika, an open-source GNSS processing library, is also introduced here. Laika produces 40% more accurate positions than the GNSS module used to collect the raw data. This dataset includes pose (position + orientation) estimates in a global reference frame of the recording camera. These poses were computed with a tightly coupled INS/GNSS/Vision optimizer that relies on data processed by Laika. comma2k19 is ideal for development and validation of tightly coupled GNSS algorithms and mapping algorithms that work with commodity sensors.
Use case
RL agent capable of assisting the driver on the fast lane by maintaining trajectory and speed while minimising fuel consumption
| Example observations | vehicle speed (km/h) long./lat. accelerations yaw-rate, roll, pitch steer-angle throttle-pos, brake-pressure heading (GIGN/IMU) lane-curvature (derived from yaw + HD maps) |
| Example actions | steering angle command throttle opening percentage brake pressure |
| Example reward | w₁ · (−|dev_lat|) # lane keeping + w₂ · (−|vₜ − v_target|) # speed tracking + w₃ · (−fuel_rate) # fuel efficiency + w₄ · (−jerk²) # comfort + segment_completion_bonus # segment completed without safety alerts Typical weights: w₁ = 0.4, w₂ = 0.3, w₃ = 0.2, w₄ = 0.1. |