INTERACTION
Autonomous Driving
|...
许可协议: Unknown

Overview

The INTERACTION dataset contains naturalistic motions of various traffic participants in a variety of highly interactive driving scenarios from different countries. More details and format of the dataset can be found here. The dataset can serve for many behavior-related research areas, such as:

  1. intention/behavior/motion prediction,
  2. behavior cloning and imitation learning,
  3. behavior analysis and modeling,
  4. motion pattern and representation learning,
  5. interactive behavior extraction and categorization,6) social and human-like behavior generation,
  6. decision-making and planning algorithm development and verification,
  7. driving scenario/case generation, etc.

Meta Information of the Track Files

This file contains all time-dependent values for each track. Information such as track id, vehicle types, vehicle sizes, current positions, current velocities, and orientations are included.

Recorded Vehicle Tracks Files (vehicle_tracks_xxx.csv)

track_id: column 1. For each vehicle_tracks_xxx.csv file, the track_id starts from 1, and represent the ID of the agent. frame_id: column 2. For each agent (per track_id), frame_id starts from 1 and represents the frames the agent appears in the video. timestamp_ms: column 3. For each agent (per track_id), timestamp_ms from 100ms, and represents the time the agent appears in the video. The unit is ms. agent_type: column 4. It represents the types of tracked agents. For example, it can be a car, a truck and so on. x: column 5, the x position of the agent at each frame. The unit is m. y: column 6, the y position of the agent at each frame. The unit is m. vx: column 7, the velocity of the agent along x-direction at each frame. The unit is m/s. vy: column 8, the velocity of the agent along y-direction at each frame. The unit is m/s. psi_rad: column 9, the yaw angle of the agent at each frame. The unit is rad. length: column 10, the length of the agent. The unit is m. width: column 11, the width of the agent. The unit is m.

Example

img

Recorded Pedestrian Track Files (pedestrian_tracks_xxx.csv)

track_id: column 1. For each person_tracks_xxx.csv file, the track_id starts from P1, and represent the ID of the agent. frame_id: column 2. For each agent (per track_id), frame_id starts from 1 and represents the frames the agent appears in the video. timestamp_ms: column 3. For each agent (per track_id), timestamp_ms from 100ms, and represents the time the agent appears in the video. The unit is ms. agent_type: column 4. It represents the types of tracked agents as "pedestrian/bicycle". x: column 5, the x position of the agent at each frame. The unit is m. y: column 6, the y position of the agent at each frame. The unit is m. vx: column 7, the velocity of the agent along x-direction at each frame. The unit is m/s. vy: column 8, the velocity of the agent along y-direction at each frame. The unit is m/s. img

Citation

Please use the following citation when referencing the dataset:

@article{interactiondataset,
title = {{INTERACTION} {Dataset}: {An} {INTERnational}, {Adversarial} and {Cooperative} {moTION}
{Dataset} in {Interactive} {Driving} {Scenarios} with {Semantic} {Maps}},
journal = {arXiv:1910.03088 [cs, eess]},
author = {Zhan,
Wei and Sun, Liting and Wang, Di and Shi, Haojie and Clausse, Aubrey and Naumann, Maximilian
and K\"ummerle, Julius and K\"onigshof, Hendrik and Stiller, Christoph and de La Fortelle,
Arnaud and Tomizuka, Masayoshi},
month = sep,
year = {2019}}
数据概要
数据格式
Image,
数据量
--
文件大小
--
发布方
MSC Lab(Mechanical Systems Control)
The recent research of MSC lab has focused on intelligent/autonomous mechanical systems and their interaction with humans from manufacturing (industrial robots) to transportation (autonomous driving) with synergies between model-based control methodologies with machine learning.
数据集反馈
| 21 | 数据量 -- | 大小 --
INTERACTION
Autonomous Driving
许可协议: Unknown

Overview

The INTERACTION dataset contains naturalistic motions of various traffic participants in a variety of highly interactive driving scenarios from different countries. More details and format of the dataset can be found here. The dataset can serve for many behavior-related research areas, such as:

  1. intention/behavior/motion prediction,
  2. behavior cloning and imitation learning,
  3. behavior analysis and modeling,
  4. motion pattern and representation learning,
  5. interactive behavior extraction and categorization,6) social and human-like behavior generation,
  6. decision-making and planning algorithm development and verification,
  7. driving scenario/case generation, etc.

Meta Information of the Track Files

This file contains all time-dependent values for each track. Information such as track id, vehicle types, vehicle sizes, current positions, current velocities, and orientations are included.

Recorded Vehicle Tracks Files (vehicle_tracks_xxx.csv)

track_id: column 1. For each vehicle_tracks_xxx.csv file, the track_id starts from 1, and represent the ID of the agent. frame_id: column 2. For each agent (per track_id), frame_id starts from 1 and represents the frames the agent appears in the video. timestamp_ms: column 3. For each agent (per track_id), timestamp_ms from 100ms, and represents the time the agent appears in the video. The unit is ms. agent_type: column 4. It represents the types of tracked agents. For example, it can be a car, a truck and so on. x: column 5, the x position of the agent at each frame. The unit is m. y: column 6, the y position of the agent at each frame. The unit is m. vx: column 7, the velocity of the agent along x-direction at each frame. The unit is m/s. vy: column 8, the velocity of the agent along y-direction at each frame. The unit is m/s. psi_rad: column 9, the yaw angle of the agent at each frame. The unit is rad. length: column 10, the length of the agent. The unit is m. width: column 11, the width of the agent. The unit is m.

Example

img

Recorded Pedestrian Track Files (pedestrian_tracks_xxx.csv)

track_id: column 1. For each person_tracks_xxx.csv file, the track_id starts from P1, and represent the ID of the agent. frame_id: column 2. For each agent (per track_id), frame_id starts from 1 and represents the frames the agent appears in the video. timestamp_ms: column 3. For each agent (per track_id), timestamp_ms from 100ms, and represents the time the agent appears in the video. The unit is ms. agent_type: column 4. It represents the types of tracked agents as "pedestrian/bicycle". x: column 5, the x position of the agent at each frame. The unit is m. y: column 6, the y position of the agent at each frame. The unit is m. vx: column 7, the velocity of the agent along x-direction at each frame. The unit is m/s. vy: column 8, the velocity of the agent along y-direction at each frame. The unit is m/s. img

Citation

Please use the following citation when referencing the dataset:

@article{interactiondataset,
title = {{INTERACTION} {Dataset}: {An} {INTERnational}, {Adversarial} and {Cooperative} {moTION}
{Dataset} in {Interactive} {Driving} {Scenarios} with {Semantic} {Maps}},
journal = {arXiv:1910.03088 [cs, eess]},
author = {Zhan,
Wei and Sun, Liting and Wang, Di and Shi, Haojie and Clausse, Aubrey and Naumann, Maximilian
and K\"ummerle, Julius and K\"onigshof, Hendrik and Stiller, Christoph and de La Fortelle,
Arnaud and Tomizuka, Masayoshi},
month = sep,
year = {2019}}
数据集反馈
0
立即开始构建AI
graviti
wechat-QR
长按保存识别二维码,关注Graviti公众号