Inspired by frame-based methods, state-of-the-art event-based optical flow networks rely on the explicit construction of correlation volumes, which are expensive to compute and store, rendering them unsuitable for robotic applications with limited compute and energy budget. Moreover, correlation volumes scale poorly with resolution, prohibiting them from estimating high-resolution flow. We observe that the spatiotemporally continuous traces of events provide a natural search direction for seeking pixel correspondences, obviating the need to rely on gradients of explicit correlation volumes as such search directions. We introduce IDNet (Iterative Deblurring Network), a lightweight yet high-performing event-based optical flow network directly estimating flow from event traces without using correlation volumes. We further propose two iterative update schemes: "ID"which iterates over the same batch of events, and "TID"which iterates over time with streaming events in an online fashion. Our top-performing model (ID) sets a new state of the art on DSEC benchmark. Meanwhile, the base model (TID) is competitive with prior arts while using 80% fewer parameters, consuming 20x less memory footprint and running 40% faster on the NVidia Jetson Xavier NX. Furthermore, the TID scheme is even more efficient offering an additional 5x faster inference speed and 8 ms ultra-low latency at the cost of only a 9% performance drop, making it the only model among current literature capable of real-time operation while maintaining decent performance.Code: https://github.com/tudelft/idnet.

@en

Biological sensing and processing is asynchronous and sparse, leading to low-latency and energy-efficient perception and action. In robotics, neuromorphic hardware for event-based vision and spiking neural networks promises to exhibit similar characteristics. However, robotic implementations have been limited to basic tasks with low-dimensional sensory inputs and motor actions because of the restricted network size in current embedded neuromorphic processors and the difficulties of training spiking neural networks. Here, we present a fully neuromorphic vision-to- control pipeline for controlling a flying drone. Specifically, we trained a spiking neural network that accepts 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 28,800 neurons, maps incoming raw events to ego-motion estimates and was trained with self-supervised learning on real event data. The control part consists of a single decoding layer and was 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 could accurately control its ego-motion, 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 hertz, consuming 0.94 watt of idle power and a mere additional 7 to 12 milliwatts when running the network. These results illustrate the potential of neuromorphic sensing and processing for enabling insect-sized intelligent robots.@en

In the ever-evolving landscape of robotics, the quest for advanced synthetic machines that seamlessly integrate with human lives and society becomes increasingly paramount. At the heart of this pursuit lies the intrinsic need for these machines to perceive, understand, and navigate their surroundings autonomously. Among the senses, vision emerges as a cornerstone of human perception, providing a wealth of information about the world we inhabit. Thus, it comes as no surprise that equipping robots with vision-based perception capabilities, or computer vision, has captivated researchers for decades. Recent breakthroughs, fueled by the advent of deep learning, have propelled computer vision to new heights. However, challenges persist in leveraging the power of deep learning, as its hunger for computational resources poses hurdles in the realm of robotics, particularly for small flying robots with their inherent limitations of payload and power consumption. This dissertation embarks on a journey that begins at the intersection of two groundbreaking technologies with the potential to revolutionize computer vision and enhance its accessibility to small robots: event-based cameras and neuromorphic processors. These two technologies draw inspiration from the information processing mechanisms employed by biological brains. Event-based cameras output sparse events encoding pixel-level brightness changes at microsecond resolution, while neuromorphic processors leverage the power of spiking neural networks to realize a sparse and asynchronous processing pipeline. 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. Overall, our studies demonstrate the benefits of incorporating neuromorphic technology into the vision-based state estimation pipeline of autonomous flying robots, paving the way for the development of more power-efficient and faster neuromorphic vision systems.@en

Nano quadcopters are small, agile, and cheap platforms that are well suited for deployment in narrow, cluttered environments. Due to their limited payload, these vehicles are highly constrained in processing power, rendering conventional vision-based methods for safe and autonomous navigation incompatible. Recent machine learning developments promise high-performance perception at low latency, while dedicated edge computing hardware has the potential to augment the processing capabilities of these limited devices. In this work, we present NanoFlowNet, a lightweight convolutional neural network for real-time dense optical flow estimation on edge computing hardware. We draw inspiration from recent advances in semantic segmentation for the design of this network. Additionally, we guide the learning of optical flow using motion boundary ground truth data, which improves performance with no impact on latency. Validation results on the MPI-Sintel dataset show the high performance of the proposed network given its constrained architecture. Additionally, we successfully demonstrate the capabilities of NanoFlowNet by deploying it on the ultra-low power GAP8 microprocessor and by applying it to vision-based obstacle avoidance on board a Bitcraze Crazyflie, a 34 g nano quadcopter.

@en

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, and usually fails to deliver on these promises. 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. Results across multiple datasets confirm the effectiveness of our method, which establishes a new state of the art in terms of accuracy for approaches trained or optimized without ground truth.

@en

End-to-end trained convolutional neural networks have led to a breakthrough in optical flow estimation. The most recent advances focus on improving the optical flow estimation by improving the architecture and setting a new benchmark on the publicly available MPI-Sintel dataset. Instead, in this article, we investigate how deep neural networks estimate optical flow. A better understanding of how these networks function is important for (i) assessing their generalization capabilities to unseen inputs, and (ii) suggesting changes to improve their performance. 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.

@en

Neuromorphic processors like Loihi offer a promising alternative to conventional computing modules for endowing constrained systems like micro air vehicles (MAVs) with robust, efficient and autonomous skills such as take-off and landing, obstacle avoidance, and pursuit. However, a major challenge for using such processors on robotic platforms is the reality gap between simulation and the real world. In this study, we present for the very first time a fully embedded application of the Loihi neuromorphic chip prototype in a flying robot. A spiking neural network (SNN) was evolved to compute the thrust command based on the divergence of the ventral optic flow field to perform autonomous landing. Evolution was performed in a Python-based simulator using the PySNN library. The resulting network architecture consists of only 35 neurons distributed among 3 layers. Quantitative analysis between simulation and Loihi reveals a root-mean-square error of the thrust setpoint as low as 0.005 g, along with a 99.8% matching of the spike sequences in the hidden layer, and 99.7% in the output layer. The proposed approach successfully bridges the reality gap, offering important insights for future neuromorphic applications in robotics. Supplementary material is available at https://mavlab.tudelft.nl/loihi/.@en

Event cameras are novel vision sensors that sample, in an asynchronous fashion, brightness increments with low latency and high temporal resolution. The resulting streams of events are of high value by themselves, especially for high speed motion estimation. However, a growing body of work has also focused on the reconstruction of intensity frames from the events, as this allows bridging the gap with the existing literature on appearance- and frame-based computer vision. Recent work has mostly approached this problem using neural networks trained with synthetic, ground-truth data. In this work we approach, for the first time, the intensity reconstruction problem from a self-supervised learning perspective. Our method, which leverages the knowledge of the inner workings of event cameras, 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 self-supervised approach is in line with the state-of-the-art. Additionally, we propose a novel, lightweight neural network for optical flow estimation that achieves high speed inference with only a minor drop in performance.@en

Flying insects are capable of vision-based navigation in cluttered environments, reliably avoiding obstacles through fast and agile maneuvers, while being very efficient in the processing of visual stimuli. Meanwhile, autonomous micro air vehicles still lag far behind their biological counterparts, displaying inferior performance at a much higher energy consumption. In light of this, we want to mimic flying insects in terms of their processing capabilities, and consequently show the efficiency of this approach in the real world. This letter does so through evolving spiking neural networks for controlling landings of micro air vehicles using optical flow divergence from 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 be learned with only a single spiking neuron. To the best of our knowledge, this work is the first to integrate spiking neural networks in the control loop of a real-world flying robot. Videos of the experiments can be found at https://bit.ly/neuro-controller.

@en

This paper gathers the design and implementation of the control system that allows an unmanned Flying-wing to perform a Vertical Take-Off and Landing (VTOL) maneuver using two tilting rotors (Bi-Rotor). Unmanned Aerial Vehicles (UAVs) operating in this configuration are also categorized as Hybrid UAVs due to their ability of having a dual flight envelope: hovering like a multi-rotor and cruising like a traditional fixed-wing, providing the opportunity of facing complex missions in which these two different dynamics are required. This work exhibits the Bi-Rotor nonlinear dynamics, the attitude tracking controller design and also, the results obtained through Hardware-In-the-Loop (HIL) simulation and experimental studies that ensure the controller’s efficiency in hovering operation.

@en

The combination of spiking neural networks and event-based vision sensors holds the potential of highly efficient and high-bandwidth optical flow estimation. This paper presents the first hierarchical spiking architecture in which motion (direction and speed) selectivity emerges in an unsupervised fashion from the raw 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. The proposed solution is validated using synthetic and real event sequences. Along with this paper, we provide the cuSNNlibrary, a framework that enables GPU-accelerated simulations of large-scale spiking neural networks. Source code and samples are available at https://github.com/tudelft/cuSNN.@en