DeepAI AI Chat
Log In Sign Up

ROAD: The ROad event Awareness Dataset for Autonomous Driving

by   Gurkirt Singh, et al.

Humans approach driving in a holistic fashion which entails, in particular, understanding road events and their evolution. Injecting these capabilities in an autonomous vehicle has thus the potential to take situational awareness and decision making closer to human-level performance. To this purpose, we introduce the ROad event Awareness Dataset (ROAD) for Autonomous Driving, to our knowledge the first of its kind. ROAD is designed to test an autonomous vehicle's ability to detect road events, defined as triplets composed by a moving agent, the action(s) it performs and the corresponding scene locations. ROAD comprises 22 videos, originally from the Oxford RobotCar Dataset, annotated with bounding boxes showing the location in the image plane of each road event. We also provide as baseline a new incremental algorithm for online road event awareness, based on inflating RetinaNet along time, which achieves a mean average precision of 16.8 detection, respectively, at 50 highlight the challenges faced by situation awareness in autonomous driving. Finally, ROAD allows scholars to investigate exciting tasks such as complex (road) activity detection, future road event anticipation and the modelling of sentient road agents in terms of mental states. Dataset can be obtained from and baseline code from


page 8

page 10


Action Detection from a Robot-Car Perspective

We present the new Road Event and Activity Detection (READ) dataset, des...

Bi-Mapper: Holistic BEV Semantic Mapping for Autonomous Driving

A semantic map of the road scene, covering fundamental road elements, is...

A Benchmark for Cycling Close Pass Near Miss Event Detection from Video Streams

Cycling is a healthy and sustainable mode of transport. However, interac...

ROAD-R: The Autonomous Driving Dataset with Logical Requirements

Neural networks have proven to be very powerful at computer vision tasks...

On the Road with 16 Neurons: Mental Imagery with Bio-inspired Deep Neural Networks

This paper proposes a strategy for visual prediction in the context of a...

TartanDrive: A Large-Scale Dataset for Learning Off-Road Dynamics Models

We present TartanDrive, a large scale dataset for learning dynamics mode...

DOROTHIE: Spoken Dialogue for Handling Unexpected Situations in Interactive Autonomous Driving Agents

In the real world, autonomous driving agents navigate in highly dynamic ...

Code Repositories


Download and pre-processing of ROAD dataset

view repo