Search papers, labs, and topics across Lattice.
This paper presents a novel instance segmentation framework tailored for autonomous lunar missions, addressing the challenges of low-light conditions, limited computational resources, and potential radiation-induced hardware faults. The authors introduce Activation Variance Informative Sampling (AVIS) for efficient quantization calibration and deploy a modified YOLO-based segmentation model on a Deep Learning Processor Unit (DPU) to ensure low-latency performance. The integrated approach achieves a 69.8% recovery of accuracy loss due to quantization while significantly reducing fault exposure, demonstrating a reliable AI perception system for resource-constrained space robotics.
AVIS recovers nearly 70% of accuracy loss from quantization while ensuring real-time performance on lunar rovers, even under radiation constraints.
Autonomous lunar missions require real-time per- ception under three coupled constraints: extreme low-light conditions, limited onboard compute, and radiation-induced hardware faults that can silently corrupt inference. We present a deployment-oriented instance segmentation framework for resource-constrained lunar robotics that jointly addresses quan- tization calibration and system-level fault exposure under strict compute constraints. First, we introduce Activation Variance Informative Sampling (AVIS), a label-free calibration strategy that deterministically selects calibration samples based on activation variance statistics. Second, we deploy a YOLO-based segmentation model on a Deep Learning Processor Unit (DPU) with architectural modifications that reduce CPU fallback paths and enable statically compiled execution with bounded latency in low-lighting conditions. We further introduce a software-level criticality analysis to estimate fault exposure and guide mitigation under radiation-constrained operation. On a lunar micro-rover platform, AVIS with bias correction recovers 69.8% of quantization-induced accuracy loss while achieving 309 ms inference latency and 5.7 W power consumption. Targeted mitigation reduces global criticality by 31.7%. The results demonstrate an integrated approach and a blueprint for a reliable and safe AI perception framework under space deployment constraints.
