Ultra-CAN: A Lightweight Blind ISAC Receiver for Chaos-Based Telemetry and Local-Seed Ranging in the Internet of Drones
Authors: Ettore Caruso, Marco Siino, Giacomo Morabito
Organizations: Politecnico di Torino, 10129 Torino, Italy · Department of Industrial, Electrical, Electronic and Computer Engineering (DIEEI), University of Catania, 95125 Catania, Italy
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 64-dimensional representation with two ultra-light backbones, an attention-pooled Conv1D network and a multi-head QKV network (27.6k--44.2k parameters), feeding communication and sensing heads. Both ship as int8 TensorFlow Lite Micro firmware; the Conv1D receiver decides a burst in 16.9 ms on a 240 MHz microcontroller with 24.2 KiB of activations, a measured energy of 2.2-3.4 mJ per burst, and float-equivalent decisions, sustaining up to 59 bit/s of telemetry or a 7.4 Hz range track. The two variants rank first and second among learned demodulators in four aerial swarm scenarios, with a pooled BER down to 4.6×10−4 on the single-echo link (2.4×10−3 with three echoes). Its sensing head identifies true obstacles in 66.8% of peer-laden bursts (vs 42% matched filtering, 44% OFDM-ISAC, 48% peak-picker ceiling). A peer-exclusion gate cuts peer reports from 4.4% to 0.02% of answered bursts, answering 23.5% of total bursts (75% on the exact tap) with 0.70 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 6--9 dB margin against partial-band jamming.
Figures & tables
Parameter
Value
Carrier / sampling
fc=2.4 GHz, fs=10 MHz
Sequence length
Nseq=100 (coherent time 10μ s)
Maps
Logistic ( μ=3.9 ), Bernoulli (5 branches)
SNR grid
{−5,−3,…,19,21} dB
Number of echoes K
{1,3} (single echo or multi-echo)
Delay τ
1 – 33 samples ( 15 m per sample)
TABLE I: Aerial ISAC link parameters.
Fig. 1: Proposed Ultra-CAN dual-mode ISAC receiver: peer-telemetry reception and local-seed monostatic radar share the Conv1D backbone, the two aggregation variants, and the communication, sensing and range-gate heads.
Fig. 2: BER against SNR over the full grid: (a) single echo, (b) multi-echo, (c) multi-echo, reduced Doppler. The blind statistical receiver is included; the proposed variants are the blue and red curves.
Condition
Correlator
Matched filter
Energy det.
K=1
0.269
0.024
0.50
K=5
0.293
0.056
0.50
K=10
0.329
0.098
0.50
fD=0
0.283
0.039
0.50
fD=1.1×10−3
0.304
0.072
0.50
fD=3.0×10−3
0.374
0.406
0.50
TABLE II: Classical baselines on the noise-free link.
Scenario
Conv1D
QKV
LSTM
MC-DLCSK
Single echo
5.08×10−4
4.64×10−4
6.10×10−4
5.53×10−4
Multi-echo
3.20×10−3
2.41×10−3
3.57×10−3
3.83×10−3
Reduced Doppler
3.18×10−3
2.42×10−3
3.51×10−3
3.58×10−3
Multi-echo + peers
2.37×10−3
1.76×10−3
4.21×10−2
4.58×10−3
TABLE III: Pooled BER; best in bold.
reported tap [% of answered bursts]
Method
obst.
peer
clutter
ans.
Chaotic MF
42.4
17.4
40.2
100
OFDM-ISAC, 60 kHz
44.2
17.9
37.9
100
OFDM-ISAC, 15 kHz
44.3
17.8
37.9
100
Peak-picker ceiling
48.0
—
—
100
Ultra-CAN (Conv1D)
66.8
4.4
28.7
100
TABLE IV: Sensing outcome at 21 dB on 200,000 peer-laden bursts.
Fig. 3: Ranging on 200,000 peer-laden bursts at 21 dB: (a) mean range error of the answered bursts and (b) reported outcome, against the obstacle-to-peer echo ratio.
Channel
Ppeak
pooled BER
ρτ
Conv1D
QKV
Conv1D
QKV
nominal
0.455
3.20×10−3
2.41×10−3
0.486
0.493
TDL-D (LOS)
0.026
3.77×10−1
3.60×10−1
0.008
0.007
TDL-D, 5% clutter
0.026
3.35×10−1
3.12×10−1
0.009
0.011
TDL-A (NLOS)
0.026
3.84×10−1
3.70×10−1
0.009
0.009
two-ray + Jakes
0.027
3.38×10−1
3.17×10−1
0.006
0.012
TABLE V: Cross-channel; best in bold.
Fig. 4: Median absolute velocity error of the model-free profile tracker against the number of bursts averaged into the track, over thirty tracks of 50 bursts.
Fig. 5: Retraining control on the TDL-D link: nominal channel (grey dotted), frozen TDL-D (red solid) and TDL-D retrained on 105,000 symbols (blue dashed), for the two backbones.
BER
margin
Condition
clean
aware
clean
aware
clean
0.0048
0.0077
2.87
2.72
CW, −2 dB
0.356
0.021
0.91
2.53
CW, +6 dB
0.405
0.110
0.34
1.63
fixed-partial, −2 dB
0.245
0.041
1.49
2.36
fixed-partial, +2 dB
0.445
0.081
0.41
2.01
TABLE VI: Jamming-aware training of the QKV receiver.
Archetype
f
BER aligned
Predicted
Measured
G
barrage
1.000
0.480
0.480
0.481
0.0
fixed-partial
0.250
0.480
0.400
0.401
6.0
blind sweep
0.122
0.484
0.389
0.390
9.1
TABLE VII: Mixing law at JSR +10 dB.
Receiver
params
f32
int8
arena
tr [ms]
Ultra-CAN (Conv1D)
27,620
107.9
45.6
24.2
16.90
Ultra-CAN-QKV
44,195
172.6
78.8
185.6
193.66
TABLE VIII: Deployment cost on the ESP32-S3.
Fig. 6: Deployment platform: the ESP32-S3-DevKitC-1 ( 240 MHz, 512 KiB of SRAM, no accelerator) on which both int8 receivers were measured, running TensorFlow Lite Micro with the ESP-NN int8 kernels. The 10 MS/s I/Q front end that feeds the two input channels is outside this digital accounting.
We investigate an integrated sensing and communication (ISAC)-enabled BS for the unmanned aerial vehicle (UAV) obstacle avoidance task, and propose a goal-oriented semantic communication (GOSC) framework for the BS to transmit sensing and command and control (C&C) signals efficiently and effectively. Our GOSC framework establishes a closed loop for sensing-C&C generation-sensing and C&C transmission: For sensing, a Kalman filter (KF) is applied to continuously predict UAV positions, mitigating the reliance of UAV position acquisition on continuous sensing signal transmission, and enhancing position estimation accuracy through sensing-prediction fusion. Based on the refined estimation position provided by the KF, we develop a Mahalanobis distance-based dynamic window approach (MD-DWA) to generate precise C&C signals under uncertainty, in which we derive the mathematical expression of the minimum Mahalanobis distance required to guarantee collision avoidance. Finally, for efficient sensing and C&C signal transmission, we propose an effectiveness-aware deep Q-network (E-DQN) to determine the transmission of sensing and C&C signals based on their value of information (VoI). The VoI of sensing signals is quantified by the reduction in uncertainty entropy of UAV's position estimation, while the VoI of C&C signals is measured by their contribution to UAV navigation improvement. Extensive simulations validate the effectiveness of our proposed GOSC framework. Compared to the conventional ISAC transmission framework that transmits sensing and C&C signals at every time slot, GOSC achieves the same 100% task success rate while reducing the number of transmitted sensing and C&C signals by 92.4% and the number of transmission time slots by 85.5%.
Wenjie Liu, Yansha Deng, Henk Wymeersch
Department of Engineering, King’s College London, Strand, London WC2R 2LS, U.K. · Department of Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden.
Communication in latent space offers an intriguing alternative to symbolic messages for decentralized autonomous Unmanned Aerial Vehicle (UAV) swarms operating over bandwidth-constrained, time-varying wireless links. However, when homogeneous frozen models are prompted with discretized perceptual inputs, their broadcast states collapse toward the shared prompt template. In view of this, we propose AeroLat, a channel-aware latent semantic communication framework that uses evidence injection. The resulting latent states are then passed through an explicit communication model that encompasses bandwidth-limited serialization, additive noise and information staleness, which facilitates a joint assessment of communication fidelity and swarm-level coordination. Across multi-seed simulations, AeroLat provably remains resilient to codec choice, faults and increasing swarm size. It consistently reproduces the latent-swarm anomaly, while no-whitening controls recover the collapse. In particular, AeroLat is capable of reducing false similarity by 97.5%.
Future integrated sensing and communication (ISAC) architectures separate the sensing entity (SE) that acquires measurements from the sensing function (SF) that performs inference, creating a need for compact, task-oriented feedback on the SE-SF interface. Forwarding the raw channel frequency response or full per-link delay-Doppler-azimuth-elevation (DDAE) tensor is prohibitively expensive, while peak-only reporting discards target-discriminative structure under clutter. We propose a learning-based coarse-to-fine sensing pipeline with candidate-latent feedback for single-target estimation. At the SE, a lightweight convolutional scorer produces a dense delay-Doppler proposal map from pilot-based OFDM channel estimates, and a learned encoder constructs K compact C-dimensional candidate tokens by fusing per-candidate azimuth-elevation patches, normalized position, and confidence cues. The latents are uniformly quantized post-training to b bits and transmitted under a finite budget B_fb = bKC + 18K + 16 bits to the SF, which performs cross-candidate refinement, reranking, and joint four-parameter estimation. On a ray-traced urban scene with static and dynamic clutter, three operating points in the (K, C, b) design space achieve 96.33-98.88% detection at 107-806 bytes per coherent processing interval, compression ratios of 1.2-9.2 x 10^4 over the 8-bit DDAE magnitude tensor, reducing the SE-SF interface from multi-Gbit/s to sub-Mbit/s rates. Cross-scene evaluation on an independent campus-scale environment achieves 98.79-99.50% detection and at-or-better angular accuracy without retraining, indicating that the learned representation captures target-relevant structure that transports across scenes of comparable or lower clutter density.