ROAD-R: The Autonomous Driving Dataset with Logical Requirements

@article{Giunchiglia2022ROADRTA,
  title={ROAD-R: The Autonomous Driving Dataset with Logical Requirements},
  author={Eleonora Giunchiglia and Mihaela Stoia and Salman Khan and Fabio Cuzzolin and Thomas Lukasiewicz},
  journal={ArXiv},
  year={2022},
  volume={abs/2210.01597}
}
Neural networks have proven to be very powerful at computer vision tasks. However, they often exhibit unexpected behaviours, violating known requirements expressing background knowledge. This calls for models (i) able to learn from the requirements, and (ii) guaranteed to be compliant with the requirements themselves. Unfortunately, the development of such models is hampered by the lack of datasets equipped with formally specified requirements. In this paper, we introduce the ROad event… 

References

SHOWING 1-10 OF 22 REFERENCES

ROAD: The Road Event Awareness Dataset for Autonomous Driving

The ROad event Awareness Dataset (ROAD) for Autonomous Driving is introduced, to the authors' knowledge the first of its kind, designed to test an autonomous vehicle’s ability to detect road events, defined as triplets composed by an active agent, the action it performs and the corresponding scene locations.

MultiplexNet: Towards Fully Satisfied Logical Constraints in Neural Networks

This work proposes a novel way to incorporate expert knowledge into the training of deep neural networks by representing domain knowledge as a quantifier-free logical formula in disjunctive normal form (DNF) which is easy to encode and to elicit from human experts.

A Semantic Loss Function for Deep Learning with Symbolic Knowledge

A semantic loss function is derived from first principles that bridges between neural output vectors and logical constraints and significantly increases the ability of the neural network to predict structured objects, such as rankings and paths.

Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

I3D models considerably improve upon the state-of-the-art in action classification, reaching 80.2% on HMDB-51 and 97.9% on UCF-101 after pre-training on Kinetics, and a new Two-Stream Inflated 3D Conv net that is based on 2D ConvNet inflation is introduced.

Recurrent Convolutions for Causal 3D CNNs

A novel Recurrent Convolutional Network (RCN), which relies on recurrence to capture the temporal context across frames at each network level, and which performs comparably to anti-causal 3D CNNs, while being causal and using fewer parameters.

HLVU: A New Challenge to Test Deep Understanding of Movies the Way Humans do

The objective is to benchmark if a computer system can "understand" non-explicit but obvious relationships the same way humans do when they watch the same movies.

Recurrent Tubelet Proposal and Recognition Networks for Action Detection

This work presents a novel deep architecture called Recurrent Tubelet Proposal and Recognition (RTPR) networks to incorporate temporal context for action detection and conducts extensive experiments to demonstrate superior results over state-of-the-art methods.

Neuro-Symbolic Constraint Programming for Structured Prediction

Nester first uses a neural network to compute an initial prediction that may or may not satisfy the constraints, and then applies a constraint-based structured predictor to refine the raw predictions according to hard and soft constraints.

Traffic Prediction Based on Random Connectivity in Deep Learning with Long Short-Term Memory

A deep learning model based on Long Short-Term Memory, called Random Connectivity LSTM (RCLSTM), which makes a notable breakthrough in the formation of neural network, which is that the neurons are connected in a stochastic manner rather than full connected.

Augmenting Neural Networks with First-order Logic

This paper presents a novel framework for introducing declarative knowledge to neural network architectures in order to guide training and prediction, and shows that knowledge-augmented networks can strongly improve over baselines, especially in low-data regimes.