LIDAR-AD: A Decoder-Free Latent-Interaction Dreamer with Action-Residual Chains for Autonomous Driving

Autonomous driving requires long-horizon closedloop decision making in dynamic traffic environments. Latent world models offer an effective framework for this problem by enabling imagination-based decision making in compact latent spaces. However, multi-source observations contain controlirrelevant redundancy, whereas reliable driving decisions rely on risk-relevant relations, future dynamics, and continuous action adjustments. This mismatch makes observation reconstruction and absolute action modeling suboptimal for learning decisionrelevant latent dynamics. We propose LIDAR-AD, a decoderfree Latent-Interaction Dreamer with Action-Residual Chains for autonomous driving. LIDAR-AD replaces observation reconstruction with redundancy-reduced latent alignment, encouraging compact representations of risk-relevant relations in multi-source driving inputs. It further models vehicle control as residual action updates and uses residual-action sequence contrastive learning to align multi-step residual-driven rollouts with future latent states. A deterministic analysis shows that the latent-tanh residual parameterization preserves interior action reachability while representing smooth long-horizon control as compact local updates. Together, these designs improve risk-aware state abstraction, continuous-control modeling, and long-horizon dynamics prediction. Extensive experiments across diverse simulated driving scenarios demonstrate that LIDAR-AD consistently outperforms world-model baselines, achieving the highest reward and the best success rate among learning-based methods. Evaluations on nuPlan-derived log-reconstructed scenarios further demonstrate the transferability of LIDAR-AD under real-world traffic layouts.

Microwave photonic short-time Fourier transform based on stabilized period-one nonlinear laser dynamics and stimulated Brillouin scattering

A microwave photonic short-time Fourier transform (STFT) system based on stabilized period-one (P1) nonlinear laser dynamics and stimulated Brillouin scattering (SBS) is proposed. By using an optoelectronic feedback loop, the frequency-sweep optical signal generated by the P1 nonlinear laser dynamics is stabilized, which is further used in conjunction with an optical bandpass filter implemented by stimulated Brillouin scattering (SBS) to achieve the frequency-to-time mapping of microwave signals and the final STFT. By comparing the experimental results with and without optoelectronic feedback, it is found that the time-frequency diagram of the signal under test (SUT) obtained by STFT is clearer and more regular, and the frequency of the SUT measured in each frequency-sweep period is more accurate. The mean absolute error is reduced by 50% under the optimal filter bandwidth.