Efficient Onboard Spacecraft Pose Estimation with Event Cameras and Neuromorphic Hardware

2026-04-05

AI Summary

This work addresses the challenge of robust 6-degree-of-freedom relative pose estimation for spacecraft under extreme lighting conditions, high contrast, and rapid motion. To this end, the authors propose a lightweight pose estimation method that leverages event cameras and the BrainChip Akida neuromorphic processor. They train a compact keypoint regression network using event-frame representations and, for the first time, deploy an end-to-end pose estimation pipeline directly on Akida hardware. A novel quantization-aware training strategy (8/4-bit) and heatmap-based model are specifically designed to align with the Akida V1/V2 architectures, enabling conversion into a compatible spiking neural network. Experiments on the SPADES dataset demonstrate real-time inference with low latency and power consumption, with the Akida V2 heatmap model achieving superior pose accuracy in cloud-based evaluation.

Abstract

Reliable relative pose estimation is a key enabler for autonomous rendezvous and proximity operations, yet space imagery is notoriously challenging due to extreme illumination, high contrast, and fast target motion. Event cameras provide asynchronous, change-driven measurements that can remain informative when frame-based imagery saturates or blurs, while neuromorphic processors can exploit sparse activations for low-latency, energy-efficient inferences. This paper presents a spacecraft 6-DoF pose-estimation pipeline that couples event-based vision with the BrainChip Akida neuromorphic processor. Using the SPADES dataset, we train compact MobileNet-style keypoint regression networks on lightweight event-frame representations, apply quantization-aware training (8/4-bit), and convert the models to Akida-compatible spiking neural networks. We benchmark three event representations and demonstrate real-time, low-power inference on Akida V1 hardware. We additionally design a heatmap-based model targeting Akida V2 and evaluate it on Akida Cloud, yielding improved pose accuracy. To our knowledge, this is the first end-to-end demonstration of spacecraft pose estimation running on Akida hardware, highlighting a practical route to low-latency, low-power perception for future autonomous space missions.

Problem

• spacecraft pose estimation
• event cameras
• neuromorphic hardware
• autonomous rendezvous
• proximity operations

Innovation

• event cameras
• neuromorphic hardware
• spacecraft pose estimation
• spiking neural networks
• quantization-aware training