CERiL: Continuous Event-based Reinforcement Learning

no code implementations • 15 Feb 2023 • Celyn Walters, Simon Hadfield

We present a method to train on event streams derived from standard RL environments, thereby solving the proposed continuous time RL problem.

reinforcement-learning Reinforcement Learning (RL)

EDeNN: Event Decay Neural Networks for low latency vision

no code implementations • 9 Sep 2022 • Celyn Walters, Simon Hadfield

Despite the success of neural networks in computer vision tasks, digital 'neurons' are a very loose approximation of biological neurons.

Optical Flow Estimation

EVReflex: Dense Time-to-Impact Prediction for Event-based Obstacle Avoidance

no code implementations • 1 Sep 2021 • Celyn Walters, Simon Hadfield

The broad scope of obstacle avoidance has led to many kinds of computer vision-based approaches.

There and Back Again: Self-supervised Multispectral Correspondence Estimation

no code implementations • 19 Mar 2021 • Celyn Walters, Oscar Mendez, Mark Johnson, Richard Bowden

In this work, we aim to address the dense correspondence estimation problem in a way that generalizes to more than one spectrum.

Autonomous Vehicles