The coordinated control of unmanned aerial vehicles (UAVs) and unmanned ground vehicles (UGVs) offers significant advantages in applications such as surveillance, navigation, and emergency response. Effective path planning is essential in such missions, especially in complex environments where UAVs must relay accurate environmental data to assist UGVs. However, in urban environments and disaster zones, wireless communication is often unstable due to severe interference and non-line-of-sight conditions, making it difficult to support timely and accurate path planning for UAV-UGV coordination. To this end, this paper proposes a semantic communication (SemCom) framework specifically designed to enhance the reliability for UAV/UGV cooperative path planning under unreliable wireless conditions. SemCom transmits only key information for path planning, reducing transmission volume without sacrificing accuracy. Based on this framework, a SemCom transceiver is designed to fulfill the requirements of UAV-UGV cooperative path planning. Simulation results show that, compared to conventional SemCom transceivers, the proposed transceiver significantly reduces data transmission volume while maintaining path planning accuracy, thereby enhancing system collaboration efficiency.

Understanding 3D affordance is essential for agents to effectively interact with real-world environments, encompassing tasks such as manipulation and navigation. Existing methods typically support open-vocabulary queries through label-based language descriptions but often suffer from limited generalization and weak discriminative ability in their representations. However, affordance understanding requires constructing a coherent semantic landscape from fragmented linguistic expressions-one that preserves intra-class diversity while minimizing inter-class overlap. To address these challenges, we introduce Aff3DFunc, a framework designed to enhance the alignment between affordance and 3D geometry. It begins with a functional text enhancement module grounded in the Information Bottleneck (IB) principle, which strategically enriches affordance semantics by maximizing both relevance and diversity. A dual-encoder architecture is then employed to extract embeddings from both point clouds and text. To bridge the modality gap, we further propose a multilevel representation alignment strategy that incorporates supervised contrastive learning, reinforcing semantic-geometric correspondence in a part-to-whole manner. Extensive experiments demonstrate that our approach significantly enhances the understanding of affordance complexity. The learned representations exhibit high adaptability to diverse text queries, particularly in zero-shot settings. Furthermore, the real-world robot validation confirms that our method improves affordance understanding, enabling more fine-grained manipulation tasks.

Generating realistic 3D human-object interactions (HOIs) remains a challenging task due to the difficulty of modeling detailed interaction dynamics. Existing methods treat human and object motions independently, resulting in physically implausible and causally inconsistent behaviors. In this work, we present HOI-Dyn, a novel framework that formulates HOI generation as a driver-responder system, where human actions drive object responses. At the core of our method is a lightweight transformer-based interaction dynamics model that explicitly predicts how objects should react to human motion. To further enforce consistency, we introduce a residual-based dynamics loss that mitigates the impact of dynamics prediction errors and prevents misleading optimization signals. The dynamics model is used only during training, preserving inference efficiency. Through extensive qualitative and quantitative experiments, we demonstrate that our approach not only enhances the quality of HOI generation but also establishes a feasible metric for evaluating the quality of generated interactions. Project website: https://wulin97.github.io/hoi-dyn

Traditional visual Simultaneous Localization and Mapping (SLAM) methods based on point features are often limited by strong static assumptions and texture information, resulting in inaccurate camera pose estimation and object localization. To address these challenges, we present SLAM 2 , a novel semantic RGB-D SLAM system that can obtain accurate estimation of the camera pose and the 6DOF pose of other objects, resulting in complete and clean static 3D model mapping in dynamic environments. Our system makes full use of the point, line, and plane features in space to enhance the camera pose estimation accuracy. It combines the traditional geometric method with a deep learning method to detect both known and unknown dynamic objects in the scene. Moreover, our system is designed with a three-mode mapping method, including dense, semi-dense, and sparse, where the mode can be selected according to the needs of different tasks. This makes our visual SLAM system applicable to diverse application areas. Evaluation in the TUM RGB-D and Bonn RGB-D datasets demonstrates that our SLAM system achieves the most advanced localization accuracy and the cleanest static 3D mapping of the scene in dynamic environments, compared to state-of-the-art methods. Specifically, our system achieves a root mean square error (RMSE) of 0.018 m in the highly dynamic TUM w/half sequence, outperforming ORB-SLAM3 (0.231 m) and DRG-SLAM (0.025 m). In the Bonn dataset, our system demonstrates superior performance in 14 out of 18 sequences, with an average RMSE reduction of 27.3% compared to the next best method. • Semantic vSLAM fusing point, line and plane improves perception and camera pose estimation. • Dense, semi-dense and sparse modes for flexible mapping in dynamic scenes. • 6DOF pose estimation of objects for enriched semantic information in mapping. • Semantic and motion fusion enables advanced pose estimation in dynamic environments. • Depth and plane-based refinement for cleaner global static 3D point cloud maps.

Decision making at unsignalized intersections presents significant challenges for autonomous vehicles (AVs), particularly in mixed traffic scenarios where both AVs and human-driven vehicles (HDVs) must safely coordinate their movements. This paper proposes a safety-critical multi-agent Monte Carlo tree search (MCTS) framework that integrates deterministic and probabilistic predictions to enable cooperative decision making in complex intersection scenarios. The framework incorporates three main innovations: 1) a safety assessment mechanism that systematically handles AV-to-AV (V2V), AV-to-HDV (V2H), and Vehicle-to-Road (V2R) interactions using dynamic safety thresholds and spatiotemporal risk metrics, 2)an adaptive HDV behavior awareness by combining the Intelligent Driver Model (IDM) with probabilistic distributions, and 3)a multi-objective reward function optimization approach that balances safety, efficiency, and cooperation. Extensive simulations demonstrate our framework’s efficacy and superior capability in ensuring safe and efficient intersection navigation across the fully-autonomous scenario (100% AVs) and challenging mixed traffic scenario (50% AVs +50% HDVs). Compared to benchmarks, our method reduces trajectory deviations by up to 37.56% in the fully-autonomous scenario and 62.43% in the mixed traffic scenario, while maintaining significantly lower Post-Encroachment Time (PET) violations (0% and 2.8%, respectively).

Autonomous lane changing requires balancing safety, comfort, and efficiency while managing complex spatiotemporal vehicle interactions. Current methods often separate risk assessment from trajectory planning, leading to either conservative or unsafe maneuvers. This paper presents a contingency-aware spatiotemporal optimization framework that integrates dynamic risk assessment and trajectory optimization to ensure the autonomous host vehicle (HV) achieve safer, more efficient lane changes. First, the HV uses a dynamic risk field method to assess the collision risk with surrounding vehicles (SVs) in real-time, integrating dynamic obstacle interactions through modified Gaussian distributions. Second, a spatiotemporal safety corridor construction scheme leverages regression-based boundaries to transform spatiotemporal requirements into manageable optimization constraints. Third, the HV adopts a contingency-aware model predictive control framework that incorporates SVs uncertainty for human-like lane changes. The formulated optimization problem is solved using sequential quadratic programming with stability and recursive feasibility. Simulations confirm that our approach ensures safety and comfort of the HV across lane changing scenarios, achieving smoother trajectories, improved stability, and enhanced safety margins, with up to 95% reductions in longitudinal and lateral accelerations and a 27% decrease in lane-changing time.

Safety and efficiency are crucial for autonomous driving in roundabouts, especially mixed traffic with both autonomous vehicles (AVs) and human-driven vehicles. This paper presents a learning-based algorithm that promotes safe and efficient driving across varying roundabout traffic conditions. A deep Q-learning network is used to learn optimal strategies in complex multi-vehicle roundabout scenarios, while a Kolmogorov-Arnold Network (KAN) improves the AVs’ environmental understanding. To further enhance safety, an action inspector filters unsafe actions, and a route planner optimizes driving efficiency. Moreover, model predictive control ensures stability and precision in execution. Experimental results demonstrate that the proposed system consistently outperforms state-of-the-art methods, achieving fewer collisions, reduced travel time, and stable training with smooth reward convergence.

Automated Vehicles (AVs) will coexist with Human-Driven Vehicles (HDVs) for a long time. AVs must navigate safely among HDVs while maintaining smooth traffic flow. To facilitate this, the decision making system of AVs must accurately assess HDV intentions while accounting for inherent uncertainties. Current HDV intention prediction models often misclassify these intentions, leading to unsafe navigation decisions. This study introduces a three-stage Bayesian sequential game-based decision making architecture designed for AV operation. In the first stage, the AV utilizes a temporal neural network to classify vehicle intentions. In the second stage, a sequential game is solved to determine optimal actions by predicting future HDV states. The final stage, serving as a validation stage, identifies and corrects misclassifications from the first stage by predicting HDV future positions, incorporating models that account for potential deviations from the ground truth. Simulation results indicate a 93.5±0.5% accuracy in initial intention predictions, facilitating swift and effective decision making. The validation stage further enhances safety by promptly correcting errors, ensuring reliable navigation for AVs in HDV environments.

We propose an enhanced semidefinite program (SDP) relaxation to enable the tight and efficient verification of neural networks (NNs). The tightness improvement is achieved by introducing a nonlinear constraint to existing SDP relaxations previously proposed for NN verification. The efficiency of the proposal stems from the iterative nature of the proposed algorithm in that it solves the resulting non-convex SDP by recursively solving auxiliary convex layer-based SDP problems. We show formally that the solution generated by our algorithm is tighter than state-of-the-art SDP-based solutions for the problem. We also show that the solution sequence converges to the optimal solution of the non-convex enhanced SDP relaxation. The experimental results on standard benchmarks in the area show that our algorithm achieves the state-of-the-art performance whilst maintaining an acceptable computational cost.

We introduce a novel method based on semidefinite program (SDP) for the tight and efficient verification of neural networks. The proposed SDP relaxation advances the present state of the art in SDP-based neural network verification by adding a set of linear constraints based on eigenvectors. We extend this novel SDP relaxation by combining it with a branch-and-bound method that can provably close the relaxation gap up to zero. We show formally that the proposed approach leads to a provably tighter solution than the present state of the art. We report experimental results showing that the proposed method outperforms baselines in terms of verified accuracy while retaining an acceptable computational overhead.

Neuro-Fuzzy (NF) model is capable of learning the nonlinear mapping between inputs and outputs accurately from training data and is thus a powerful tool for identification of nonlinear dynamic systems. However, when deploying the trained model, the noisy measurement leads to bias model predictions. Besides, training data is insufficient to cover the whole operating space for nonlinear systems. To well capture the system response, this paper proposes a recursive least squares algorithm to enable the NF model self-adaptive to different operating conditions whilst being robustness against measurement noise. Building on the data filtering technique and the auxiliary model theory, the proposed algorithm achieves high model prediction accuracy for online implementations. Efficacy of the algorithm is demonstrated by two simulation cases.

This paper investigates cooperative adaptive cruise control (CACC) for mixed platoons consisting of both human-driven vehicles (HVs) and automated vehicles (AVs). This research is critical because the penetration rate of AVs in the transportation system will remain unsaturated for a long time. Uncertainties and randomness are prevalent in human driving behaviours and highly affect the platoon safety and stability, which need to be considered in the CACC design. A further challenge is the difficulty to know the exact models of the HVs and the exact powertrain parameters of both AVs and HVs. To address these challenges, this paper proposes a data-driven model predictive control (MPC) that does not need the exact models of HVs or powertrain parameters. The MPC design adopts the technique of data-driven reachability to predict the future trajectory of the mixed platoon within a given horizon based on noisy vehicle measurements. Compared to the classic adaptive cruise control (ACC) and existing data-driven adaptive dynamic programming (ADP), the proposed MPC ensures satisfaction of constraints such as acceleration limit and safe inter-vehicular gap. With this salient feature, the proposed MPC has provably guarantee in establishing a safe and robustly stable mixed platoon despite of the velocity changes of the leading vehicle. The efficacy and advantage of the proposed MPC are verified through comparison with the classic ACC and data-driven ADP methods on both small and large mixed platoons.

We present a novel semidefinite programming (SDP) relaxation that enables tight and efficient verification of neural networks. The tightness is achieved by combining SDP relaxations with valid linear cuts, constructed by using the reformulation-linearisation technique (RLT). The computational efficiency results from a layerwise SDP formulation and an iterative algorithm for incrementally adding RLT-generated linear cuts to the verification formulation. The layer RLT-SDP relaxation here presented is shown to produce the tightest SDP relaxation for ReLU neural networks available in the literature. We report experimental results based on MNIST neural networks showing that the method outperforms the state-of-the-art methods while maintaining acceptable computational overheads. For networks of approximately 10k nodes (1k, respectively), the proposed method achieved an improvement in the ratio of certified robustness cases from 0% to 82% (from 35% to 70%, respectively).

This paper proposes an integrated design of fault-tolerant control (FTC) for nonlinear systems using Takagi-Sugeno (T-S) fuzzy models in the presence of modeling uncertainty along with actuator/sensor faults and external disturbance. An augmented state unknown input observer is proposed to estimate the faults and system states simultaneously, and using the estimates, an FTC controller is developed to ensure robust stability of the closed-loop system. The main challenge arises from the bidirectional robustness interactions, since the fault estimation (FE) and FTC functions have an uncertain effect on each other. The proposed strategy uses a single-step linear matrix inequality formulation to integrate together the designs of FE and FTC functions to satisfy the required robustness. The integrated strategy is demonstrated to be effective through a tutorial example of an inverted pendulum system (based on robust T-S fuzzy designs).