← 研踪 PaperTrailarXiv:2611.19529 · v1
Ultra-CAN: A Lightweight Blind ISAC Receiver for Chaos-Based Telemetry and Local-Seed Ranging in the Internet of Drones
首次提交 2026-11-15 01:56
版本更新 2026-11-15 01:56
雷达观测 2026-11-17 12:06
摘要
The Internet of Drones (IoD) needs secure telemetry and proximity sensing within the SWaP-C constraints. We show that a single blind neural receiver driven by one chaos-based waveform performs both functions without a separate radar transceiver. In telemetry mode it decodes a peer's burst blindly; in radar mode it regenerates the per-burst chaotic reference locally and ranges the echoes of its own transmission. Ultra-CAN pairs a shared -dimensional representation with two ultra-light backbones, an attention-pooled Conv1D network and a multi-head QKV network (k--k parameters), feeding communication and sensing heads. Both ship as int8 TensorFlow Lite Micro firmware; the Conv1D receiver decides a burst in ms on a MHz microcontroller with KiB of activations, a measured energy of - mJ per burst, and float-equivalent decisions, sustaining up to bit/s of telemetry or a Hz range track. The two variants rank first and second among learned demodulators in four aerial swarm scenarios, with a pooled BER down to on the single-echo link ( with three echoes). Its sensing head identifies true obstacles in of peer-laden bursts (vs matched filtering, OFDM-ISAC, peak-picker ceiling). A peer-exclusion gate cuts peer reports from to of answered bursts, answering of total bursts ( on the exact tap) with m/s velocity tracking. In-domain refitting recovers telemetry BER by up to three orders of magnitude under 3GPP channels, jamming-aware training restores the link, and frequency agility adds a -- dB margin against partial-band jamming.
作者备注:14 pages, 6 figures, 9 tables. Submitted to IEEE Internet of Things Journal
观测到的版本
相邻记录可能跳过中间版本;首次发现 v2 及以上也会标为版本更新。
v1 · 2026-11-15 01:56 · 最新观测版本
Ultra-CAN: A Lightweight Blind ISAC Receiver for Chaos-Based Telemetry and Local-Seed Ranging in the Internet of Drones
The Internet of Drones (IoD) needs secure telemetry and proximity sensing within the SWaP-C constraints. We show that a single blind neural receiver driven by one chaos-based waveform performs both functions without a separate radar transceiver. In telemetry mode it decodes a peer's burst blindly; in radar mode it regenerates the per-burst chaotic reference locally and ranges the echoes of its own transmission. Ultra-CAN pairs a shared -dimensional representation with two ultra-light backbones, an attention-pooled Conv1D network and a multi-head QKV network (k--k parameters), feeding communication and sensing heads. Both ship as int8 TensorFlow Lite Micro firmware; the Conv1D receiver decides a burst in ms on a MHz microcontroller with KiB of activations, a measured energy of - mJ per burst, and float-equivalent decisions, sustaining up to bit/s of telemetry or a Hz range track. The two variants rank first and second among learned demodulators in four aerial swarm scenarios, with a pooled BER down to on the single-echo link ( with three echoes). Its sensing head identifies true obstacles in of peer-laden bursts (vs matched filtering, OFDM-ISAC, peak-picker ceiling). A peer-exclusion gate cuts peer reports from to of answered bursts, answering of total bursts ( on the exact tap) with m/s velocity tracking. In-domain refitting recovers telemetry BER by up to three orders of magnitude under 3GPP channels, jamming-aware training restores the link, and frequency agility adds a -- dB margin against partial-band jamming.
查看此版本解读 →查看此版本原文 ↗