Repository of sensor data for autonomous driving research

Abstract

We describe a project to collect and disseminate sensor data for autonomous mobility research. Our goals are to provide data of known accuracy and precision to researchers and developers to enable algorithms to be developed using realistically difficult sensory data. This enables quantitative comparisons of algorithms by running them on the same data, allows groups that lack equipment to participate in mobility research, and speeds technology transfer by providing industry with metrics for comparing algorithm performance. Data are collected using the NIST High Mobility Multi-purpose Wheeled Vehicle (HMMWV), an instrumented vehicle that can be driven manually or autonomously both on roads and off. The vehicle can mount multiple sensors and provides highly accurate position and orientation information as data are collected. The sensors on the HMMWV include an imaging ladar, a color camera, color stereo, and inertial navigation (INS) and Global Positioning System (GPS). Also available are a highresolution scanning ladar, a line-scan ladar, and a multicamera panoramic sensor. The sensors are characterized by collecting data from calibrated courses containing known objects. For some of the data, ground truth will be collected from site surveys. Access to the data is through a web-based query interface. Additional information stored with the sensor data includes navigation and timing data, sensor to vehicle coordinate transformations for each sensor, and sensor calibration information. Several sets of data have already been collected and the web query interface has been developed. Data collection is an ongoing process, and where appropriate, NIST will work with other groups to collect data for specific applications using third-party sensors.

Ground truth and benchmarks for performance evaluation

“…In our case, we commissioned a survey of the NIST campus ( In order to produce the ground truth database from a sensor or set of sensors, each sensor is mounted on the NIST HMMWV or other calibrated vehicle with an accurate position sensor, or a tripod or other stationary mount whose position can be obtained accurately. If the sensors are to be used in real time autonomous driving, the vehicle is driven over the NIST grounds, preferably over the kind of terrain on which the sensors will be used and data is collected with associated time and position stamps 19 .…”

Three-Dimensional Change Detection With the Use of an Evidence Grid

“…Data for this study were generated by an imaging ladar built by General Dynamics Robotic Systems (GDRS). The GDRS ladar has been described in Shneier et al (2003). Other imaging ladar technologies exist; several are described in Juberts and Barbera (2004).…”

Global Counterinsurgency: A Way Out of the Global War on Terrorism Quagmire?

“…Juxtaposition is the first step in fusion and requires that a number of issues be taken into account so that fusion is between consistent entities, i.e., "apples to apples". Substantial effort has been devoted to collecting multi-sensor data in the UGV context (Shneier, 2003), but few UGV implementations have taken advantage of synergies made possible by multiple sensors. The initial focus of this study was to establish confidence in the rotational egomotion extracted from forward looking camera imagery by a new implementation created by the U.S. Army Research Laboratory (ARL).…”