While Large Language Models (LLMs) enable complex autonomous behavior, current agents remain constrained by static, humandesigned prompts that limit adaptability.Existing self-improving frameworks attempt to bridge this gap but typically rely on inefficient, multi-turn recursive loops that incur high computational costs.To address this, we propose Metacognitive Agent Reflective Self-improvement (MARS), a framework that achieves efficient self-evolution within a single recurrence cycle.Inspired by educational psychology, MARS mimics human learning by integrating principle-based reflection (abstracting normative rules to avoid errors) and procedural reflection (deriving step-by-step strategies for success).By synthesizing these insights into optimized instructions, MARS allows agents to systematically refine their reasoning logic without continuous online feedback.Extensive experiments on six benchmarks demonstrate that MARS outperforms state-of-the-art self-evolving systems while significantly reducing computational overhead.

The rapid development of autonomous driving and robotics has led to increasingly higher demands for high-precision localization, making it an indispensable key component of modern autonomous systems. High-definition maps have become widely used to enhance localization accuracy, particularly in complex and dynamic environments. However, persistent challenges such as sensor measurement errors, environmental drift, and inaccuracies remain, making place recognition an increasingly critical research focus. This paper introduces a novel place recognition method based on a complex number framework, wherein environmental features are stored in both the real and imaginary parts of a complex number. This innovative approach significantly improves the richness and accuracy of environmental descriptions, thereby enhancing the system’s ability to distinguish between highly similar environments. Furthermore, a descriptor similarity evaluation strategy based on the angle between complex number vectors is proposed, which enhances the distinction of descriptors, especially in scenarios where the environments share similar characteristics, thus reducing the likelihood of mismatches. To ensure real-time performance, a hierarchical retrieval filtering process is introduced that effectively combines both coarse and fine-grained search strategies, optimizing the KD-Tree search and filtering out irrelevant matches. Experimental results on public datasets and real-world vehicle data across diverse scenarios validate the proposed method’s effectiveness and robustness, showing notable gains in recognition accuracy and real-time performance in complex environments.

Improper handling of on-ramp merging may cause severe decrease of traffic efficiency and contribute to lower fuel economy, even increasing the collision risk. Cooperative control for connected and automated vehicles (CAVs) has the potential to significantly reduce the negative impact and improve safety and traffic efficiency. Implementation of cooperative on-ramp merging requires the assistance of the vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communication, wherein the communication delay may cause negative impact on CAV cooperative control. In this paper, scenario of on-ramp merging for CAVs considering the V2I communication delay are studied. Statistical characteristics of the V2I communication delay are explored from both literature and real field test, and a communication delay estimation model based on statistical techniques are proposed. Specifically, we firstly model the CAV on-ramp merging scenario using optimal control in ideal situation. Then, several statistical characteristics of the V2I communication are investigated especially the probability density function of the V2I communication delay in several application scenarios. Further, we proposed a communication delay estimation model and used the modified vehicle state to compute the corresponding control law. Real field test of V2I communication delay indicated that distribution of V2I communication delay could correlate with the application scenario and normal distribution can be generally adopted to approximate the probability density function (PDF) when the number of samples is large enough. Numerical simulation of the CAV on-ramp merging scenario considering the V2I communication delay revealed that dynamic performance of the control process would be deteriorated impacted by the V2I communication delay and it might further impact the final control effect and lead to potential lateral collision in the merging area.