Publications

Jonathan Courtois, Benoit Miramond, Alain Pegatoquet

ESA SPAICE conference 2024

With the growing interest in on On-orbit servicing (OOS) and Active Debris Removal (ADR) missions, spacecraft poses estimation algorithms are being developed using deep learning to improve the precision of this complex task and find the most efficient solution.  With the advances of bio-inspired low-power solutions, such as spiking neural networks and event-based cameras, and their recent work for space applications, we propose to investigate the feasibility of a fully event-based solution to improve event-based pose estimation for spacecraft.  In this paper, we address the first event-based dataset SEENIC with real event frames captured with an event-based camera on a testbed.  We show the methods and results of the first event-based solution for this use case, where our small spiking end-to-end network (S2E2) solution achieves interesting results over 0.21m position error and 14.3◦ rotation error, which is the first step towards fully event-based processing for spacecraft pose estimation.

Jonathan Courtois, Pierre-Emmanuel Novac, Edgar Lemaire, Alain Pegatoquet, Benoit Miramond

2024 International Joint Conference on Neural Networks (IJCNN)

The complexity of event-based object detection (OD) poses considerable challenges. Spiking Neural Networks (SNNs) show promising results and pave the way for efficient event-based OD. Despite this success, the path to efficient SNNs on embedded devices remains a challenge. This is due to the size of the networks required to accomplish the task and the ability of devices to take advantage of SNNs benefits. Even when "edge" devices are considered, they typically use embedded GPUs that consume tens of watts. In response to these challenges, our research introduces an embedded neuromorphic testbench that utilizes the SPiking Low-power Event-based ArchiTecture (SPLEAT) accelerator. Using an extended version of the Qualia framework, we can train, evaluate, quantize, and deploy spiking neural networks on an FPGA implementation of SPLEAT. We used this testbench to load a state-of-the-art SNN …

Edgar Lemaire, Loïc Cordone, Andrea Castagnetti, Pierre-Emmanuel Novac, Jonathan Courtois, Benoît Miramond

Spiking Neural Networks are a type of neural networks where neurons communicate using only spikes. They are often presented as a low-power alternative to classical neural networks, but few works have proven these claims to be true. In this work, we present a metric to estimate the energy consumption of SNNs independently of a specific hardware. We then apply this metric on SNNs processing three different data types (static, dynamic and event-based) representative of real-world applications. As a result, all of our SNNs are 6 to 8 times more efficient than their FNN counterparts.

International Conference on Neural Information Processing

Vincent Dubancheta, Juan A Bejar Romerob, Iosif S Paraskevasc, Pablo Lopez Negroa, Aurélien Cuffoloa, Florent Mayea, Andrés Rodríguez Reinab, Pablo Romero Manriqueb, Mercedes Alonsob, Sebastian Torralbo

The emerging On-Orbit Servicing market is evolving at an unprecedented pace over the last years, driving the related European robotic technologies into a fast and agile development to meet these new needs. With that respect, the EROSS project led in the scope of the H2020 framework integrated and demonstrated the performances of an overall Servicer design towards the future on-orbit services like life extension, refuelling, and even the more futuristic scenario of a unit exchange for repair or upgrade. This paper presents the EROSS mission of application and the overall hardware and software architecture which has been validated at functional, kinematic and dynamic levels. The focus of the presented work is on the results of these experiments with orders of magnitude of the attainable performances and the level of autonomy implemented. Both open and closed loop experiments are presented along with their respective validation scope regarding the overall Servicer and Client designs. The goal of this experiments is to raise these technologies maturity towards an in-orbit demonstration by 2025.