Federico Paredes-Vallés

Senior Research Engineer at Sony

My research interest is the intersection of machine learning, neuroscience, computer vision, and robotics.

Ph.D. - Neuromorphic Computing for Flying Robots

Contact info:

Federico Paredes-Vallés

email: fedeparedesv@gmail.com

Selected Publications

Science Robotics, 2024

Here, we present the first fully neuromorphic vision-to-control pipeline for controlling a freely flying drone. Specifically, we train a spiking neural network that accepts high-dimensional raw event-based camera data and outputs low-level control actions for performing autonomous vision-based flight. The vision part of the network, consisting of five layers and 28.8k neurons, maps incoming raw events to ego-motion estimates and is trained with self-supervised learning on real event data. The control part consists of a single decoding layer and is learned with an evolutionary algorithm in a drone simulator. Robotic experiments show a successful sim-to-real transfer of the fully learned neuromorphic pipeline. The drone can accurately follow different ego-motion setpoints, allowing for hovering, landing, and maneuvering sideways, even while yawing at the same time. The neuromorphic pipeline runs on board on Intel's Loihi neuromorphic processor with an execution frequency of 200 Hz, spending only 27 µJ per inference.

TU Delft repository, 2023

Throughout this dissertation, comprehensive investigations have been conducted, presenting innovative solutions and advancements in the fields of computer vision and robotics. The thesis begins by presenting the winning solution of the 2019 AIRR autonomous drone racing competition, which showcases a monocular vision-based navigation approach specifically designed to address the limitations of conventional sensing and processing methods. Moreover, it explores the bridging of the gap between event-based and framebased domains, enabling the application of conventional computer vision algorithms on event-camera data. Building upon these achievements, the thesis introduces a pioneering spiking architecture that enables the estimation of event-based optical flow, with emergent selectivity to local and global motion through unsupervised learning. Additionally, the thesis presents a framework that addresses the practicality and deployability of the models by training spiking neural networks to estimate low-latency, event-based optical flow with self-supervised learning. Finally, this dissertation culminates with a demonstration of the integration of neuromorphic computing in autonomous flight. By utilizing an eventbased camera and neuromorphic processor in the control loop of a small flying robot for optical-flow-based navigation, this research showcases the practical implementation of neuromorphic systems in real-world scenarios.

ICCV, 2023

Event cameras have recently gained significant traction since they open up new avenues for low-latency and low-power solutions to complex computer vision problems. To unlock these solutions, it is necessary to develop algorithms that can leverage the unique nature of event data. However, the current state-of-the-art is still highly influenced by the frame-based literature. In this work, we take this into consideration and propose a novel self-supervised learning pipeline for the sequential estimation of event-based optical flow that allows for the scaling of the models to high inference frequencies. At its core, we have a continuously-running stateful neural model that is trained using a novel formulation of contrast maximization that makes it robust to nonlinearities and varying statistics in the input events.

Field Robotics, 2022

In this article, we present the winning solution of the first AI Robotic Racing (AIRR) Circuit. The core of our approach is inspired by how human pilots combine noisy observations of the race gates with a mental model of the drone’s dynamics. The navigation is based on gate detection with an efficient deep neural segmentation network and active vision. Our solution was able to reach speeds of ≈33 km/h (9.2m/s) and hereby more than triple the speeds seen in previous autonomous drone race competitions. This work analyses the performance of each component and discusses the implications for high-performance real-world AI applications with limited training time.

NeurIPS, 2021

Neuromorphic sensing and computing hold a promise for highly energy-efficient and high-bandwidth-sensor processing. In this article, we focus on the self-supervised learning problem of optical flow estimation from event-based camera inputs, and investigate the changes that are necessary to the state-of-the-art ANN training pipeline in order to successfully tackle it with SNNs. We show that the performance of the proposed ANNs and SNNs are on par with that of the current state-of-the-art ANNs trained in a self-supervised manner.

CVPR, 2021

In this work, we approach, for the first time, the event-based intensity reconstruction problem from a self-supervised learning perspective. Our framework combines estimated optical flow and the event-based photometric constancy to train neural networks without the need for any ground-truth or synthetic data. Results across multiple datasets show that the performance of the proposed approach is in line with the state-of-the-art.

The challenge, organized by Lockheed Martin and the Drone Racing League, is designed to bring artificial intelligence to the drone racing world. The difficult mix of perceiving your environment, flying as fast as possible, and performing reliably under different conditions make this a one-of-a-kind competition.

The final race, which took place in Austin, Texas, on Friday December 6, was the grand finale of a series of races which began months ago. With every race, the challenge became more exciting. Our team worked really hard throughout each stage to bring a robust and (most importantly) fast solution to the table, and we are proud to have won despite the remarkable competitors that we had to face. It was a really tight race, with the first runner up, the Robotics and Perception group from the University of Zürich, being only 3 seconds slower.


This paper presents the first hierarchical spiking architecture in which motion selectivity emerges in an unsupervised fashion from the stimuli generated with an event-based camera. A novel adaptive neuron model and stable spike-timing-dependent plasticity formulation are at the core of this neural network governing its spike-based processing and learning, respectively. After convergence, the neural architecture exhibits the main properties of biological visual motion systems, namely feature extraction and local and global motion perception. Convolutional layers with input synapses characterized by single and multiple transmission delays are employed for feature and local motion perception, respectively; while global motion selectivity emerges in a final fully-connected layer.


In this article, we investigate how deep neural networks estimate optical flow. For our investigation, we focus on FlowNetS, as it is the prototype of an encoder-decoder neural network for optical flow estimation. Furthermore, we use a filter identification method that has played a major role in uncovering the motion filters present in animal brains in neuropsychological research. The method shows that the filters in the deepest layer of FlowNetS are sensitive to a variety of motion patterns. Not only do we find translation filters, as demonstrated in animal brains, but thanks to the easier measurements in artificial neural networks, we even unveil dilation, rotation, and occlusion filters. Furthermore, we find similarities in the refinement part of the network and the perceptual filling-in process which occurs in the mammal primary visual cortex. 

RAL, 2020

We want to mimic flying insects in terms of their processing capabilities, and consequently apply gained knowledge to a maneuver of relevance. This letter does so through evolving spiking neural networks for controlling landings of micro air vehicles using the divergence of the optical flow field of a downward-looking camera. We demonstrate that the resulting neuromorphic controllers transfer robustly from a highly abstracted simulation to the real world, performing fast and safe landings while keeping network spike rate minimal. Furthermore, we provide insight into the resources required for successfully solving the problem of divergence-based landing, showing that high-resolution control can potentially be learned with only a single spiking neuron.