A predicted trajectory guidance control (PTGC) framework is proposed to deal with the degradation of maneuverability and drivability of a teleoperated ground vehicle caused by large communication delays. Humans dominate the control of the teleoperated ground vehicle, and human sensitivity to delays is the main reason for control performance degradation. To address this problem, the proposed framework predicts the teleoperator's intended trajectory using the control commands and the 3D point cloud of the environment at the vehicle side, which is then used to guide the vehicle directly. The novelty of the approach is to attenuate the sensitivity of the human-in-loop system to delays by removing the teleoperator from the direct control loop. Delays can be compensated as long as the predicted horizon exceeds the delays. Human-in-loop simulation experiments are designed to evaluate the teleoperation performance of the proposed method at various delay levels. By means of repeated measurement analysis of variance, it is concluded that the proposed method can significantly improve maneuverability and drivability metrics at large delays (>200ms), such as the task completion time, deviation to centerline and steering efforts. In addition, the results also show that since teleoperators can adapt well to small delays (≤ 200 ms), the presented method is ineffective in this case.

An eye-movement-based predicted trajectory guidance control (ePTGC) is proposed to mitigate the maneuverability degradation of a teleoperated ground vehicle caused by communication delays. Human sensitivity to delays is the main reason for the performance degradation of a ground vehicle teleoperation system. The proposed framework extracts human intention from eye-movement and combines it with contextual constraints to generate an intention-compliant guidance trajectory, which is then employed to control the vehicle directly. Using eye-movement contributes to more accurate steering intention and trajectory prediction, which is critical for trajectory guidance control. A human-in-loop simulation platform is designed to evaluate the teleoperation performance of the proposed method at different delay levels. The results are analyzed by repeated measures ANOVA, which shows that the proposed method significantly improves maneuverability and cognitive burden at large delay levels (>200ms). The overall performance is also much better than the PTGC which does not employ the eye-movement feature.

Teleoperated ground vehicles (TGVs) are widely applied in hazardous and dynamic environments, where communication delay and low transparency increase operator workload and reduce control performance. This study explores the cognitive and physiological workload associated with such conditions and evaluates the effectiveness of an eye-movement-based predicted trajectory guidance control (ePTGC) framework in alleviating operator burden. A human-in-the-loop teleoperation experiment was conducted using a 2 × 2 within-subject design, incorporating subjective ratings (NASA-TLX), objective performance metrics from a dual-task paradigm (one-back memory task), and multimodal physiological indicators (ECG and EDA). Results show that delay and low transparency significantly elevated subjective, objective, and physiological workload levels. Compared to direct control (DC), the ePTGC framework significantly reduced workload across all three dimensions, particularly under high-delay conditions, while maintaining or even improving task performance. Notably, ePTGC enabled even lower workload levels under low-delay conditions than the baseline condition. These findings demonstrate the potential of the ePTGC framework to enhance teleoperation stability and reduce operator burden in delay-prone and low-transparency scenarios.

Accurate and reliable prediction of driving intentions and future trajectories contributes to cooperation between human drivers and ADAS in complex traffic environments. This paper proposes a visual AOI (Area of Interest) based multimodal trajectory prediction model for probabilistic risk assessment at intersections. In this study, we find that the visual AOI implies the driving intention and is about 0.6–2.1 s ahead of the operation. Therefore, we designed a trajectory prediction model that integrates the driving intention (DI) and the multimodal trajectory (MT) predictions. The DI model was pre-trained independently to extract the driving intention using features including the visual AOI, historical vehicle states, and environmental context. The intention prediction experiments verify that the visual AOI-based DI model predicts steering intention 1.38 s ahead of the actual steering operation. The trained DI model is then integrated into the trajectory prediction model to filter multimodal trajectories. The trajectory prediction experiments show that the proposed model outperforms the state-of-the-art models. Risk assessment for traffics at intersections verifies that the proposed method achieves high accuracy and a low false alarm rate and identifies the potential risk about 3 s before a conflict occurs.

Accurate and reliable prediction of driving intentions and future trajectories contributes to cooperation between human drivers and ADAS in complex traffic environments. This paper proposes a visual AOI (Area of Interest) based multimodal trajectory prediction model for probabilistic risk assessment at intersections. In this study, we find that the visual AOI implies the driving intention and is about 0.6-2.1 s ahead of the operation. Therefore, we designed a trajectory prediction model that integrates the driving intention (DI) and the multimodal trajectory (MT) predictions. The DI model was pre-trained independently to extract the driving intention using features including the visual AOI, historical vehicle states, and environmental context. The intention prediction experiments verify that the visual AOI-based DI model predicts steering intention 0.925 s ahead of the actual steering operation. The trained DI model is then integrated into the trajectory prediction model to filter multimodal trajectories. The trajectory prediction experiments show that the proposed model outperforms the state-of-the-art models. Risk assessment for traffics at intersections verifies that the proposed method achieves high accuracy and a low false alarm rate, and identifies the potential risk about 3 s before a conflict occurs.