Mobile robots are increasingly playing a pivotal role in various fields, including environmental monitoring and search-and-rescue tasks. The ultimate development goal for robots is to achieve embodied artificial intelligence (embodied AI), which enables continuous learning and evolution through interactions with the environment. Motion planning and control are fundamental for robots to interact with environments and accomplish complex tasks effectively. With the rapid advancement of AI technologies, machine learning (ML) algorithms have been successfully applied to various robotic tasks. This survey provides a comprehensive overview and classification of learning-based motion planning and control approaches, which can help mobile robots achieve embodied AI. First, the existing approaches are categorized into five system architectures based on the modules applied by the ML algorithms. Second, a detailed review is provided on how reinforcement learning (RL), imitation learning, and the integration of ML with model predictive control (ML-MPC) techniques are applied across the different architectures. Additionally, the current state of research on several critical issues in embodied AI is presented, including safe learning control, Sim2Real transfer, and large language models (LLMs). Finally, the survey highlights some challenges in realizing embodied AI in real-world scenarios and suggests potential directions for future research. Unlike existing reviews that focus on specific tasks or categorize related work by ML algorithms, this survey constructs a taxonomy of existing research from a system architecture perspective. It emphasizes key technologies that facilitate real-world applications. We hope that our work will contribute to the advancement of embodied AI in the field of mobile robots.

This paper proposes a geometric-weighted Kalman consensus filter (GW-KCF) that systematically addresses distance-dependent measurement noise effects, unlike traditional methods assuming constant observation noise. The proposed framework introduces dynamic edge weight adaptation across the network to minimize estimation bias, with explicit consideration of occlusion effects through a nonlinear measurement noise model where occlusion is mathematically equivalent to infinite distance. To enhance computational efficiency, we develop a suboptimal algorithm that employs Kalman gain matrix approximation while preserving estimation accuracy. Through Lyapunov stability analysis, we provide rigorous theoretical guarantees for the estimation error dynamics. Numerical simulations reveal that the suboptimal GW-KCF achieves superior consensus accuracy and accelerated convergence speed in scenarios with significant distance-dependent noise variations. Experimental validation with three UAVs tracking a ground target demonstrates the algorithm's robustness against partial node failures, sustaining positioning accuracy within 1 % under sensor dropout conditions.

Scene graph generation (SGG) is a structured approach to understanding real-world scenes with complex relations, which can enhance UAV autonomy in unfamiliar environments. However, SGG typically has numerous model parameters that require considerable computational resources. This paper proposes a refined SGG model and reduces the model parameters for its UAV applications. First, we use subject-object query pairs to predict triplets directly, eliminating the need for separate entity predictions. Additionally, the cross-attention mechanism enhances the model’s ability to query triplets. We use a single decoder to process subject and object entities simultaneously, enhancing computational speed and reducing the number of parameters. Then, we map the entities to the relational semantic space before performing relations classification, which improves the model performance by adding a small number of parameters. Finally, the set prediction loss function is designed for relation prediction to strengthen the role of relation prediction in triplets. Real-world UAV experiments show that our model can extract more triplets per second with fewer parameters than the benchmarks. Github: https://github.com/SupersPig/myLGTR.

Accurate dynamics modeling is essential for quadrotors to achieve precise trajectory tracking in various applications. Traditional physical knowledge-driven modeling methods face substantial limitations in unknown environments characterized by variable payloads, wind disturbances, and external perturbations. On the other hand, data-driven modeling methods suffer from poor generalization when handling outof-distribution (OoD) data, restricting their effectiveness in unknown scenarios. To address these challenges, we introduce the Physics-Informed Wind-Adaptive Network (PI-WAN), which combines knowledge-driven and data-driven modeling methods by embedding physical constraints directly into the training process for robust quadrotor dynamics learning. Specifically, PI-WAN employs a Temporal Convolutional Network (TCN) architecture that efficiently captures temporal dependencies from historical flight data, while a physics-informed loss function applies physical principles to improve model generalization and robustness across previously unseen conditions. By incorporating real-time prediction results into a model predictive control (MPC) framework, we achieve improvements in closed-loop tracking performance. Comprehensive simulations and real-world flight experiments demonstrate that our approach outperforms baseline methods in terms of prediction accuracy, tracking precision, and robustness to unknown environments.

In this letter, we propose a novel multi-target association algorithm that fuses topological and visual features, and this algorithm improves target discrimination. The fused features are first constructed, and then a similarity calculation method is proposed to aggregate neighbor similarities to the central node based on topological similarity, which can be iterated several times to enhance the differentiation between targets. The experimental results demonstrate the advantages of the proposed algorithm. Github:https://github.com/SupersPig/FTVF

Complex environments pose significant challenges to the consensus estimation of ground targets by multiple autonomous aerial vehicles (multi-AAVs) with limited sensing capabilities. This paper addresses the design of an$H_{\infty } $consensus fuzzy filter over a finite-time horizon, that is subject to selective network attacks and stochastic incomplete measurements. First, a novel selective-data-based (SDB) network attack model is proposed. Unlike conventional models, this model is constructed from the attacker’s perspective to mimic attacks that target high-value data, thereby maximizing its destructive potential. Second, incomplete measurements, arising from factors such as limited AAV sensing ranges and target motion, are modeled by using a set of random variables to characterize the stochastic nature of data loss. Furthermore, an$H_{\infty } $consensus fuzzy filter is developed to achieve precise consensus estimation of the target with finite-time performance, thereby forming a unified attack-defense architecture. Sufficient conditions for the existence of such a filter are established in the form of linear matrix inequalities (LMIs), from which the filter gains can be derived. Finally, the effectiveness and superiority of the proposed design are validated through both numerical simulations and physical experiments.