arxiv.org·2026/10/23
针对旁车突然并入导致碰撞的问题，研究将基于 Knowledge Graph Embedding 与 Bayesian inference 的换道预测接入 CARLA，对比反应式驾驶、预测式纵向制动和预测式横向避让。预测器把数值特征转为 knowledge graph 三元组，经 TransE 嵌入与 Bayesian inference 输出左换道/保持/右换道；决策端按预期目标车道重排车辆，以 ∑1/TTC 车道风险选最低者，纵向用 IDM–PID，换道用 MPC 跟踪预设轨迹。在目标车强行并入场景中，预测式策略比反应式提前约 2.5 s 响应并避免碰撞。碰撞前评估窗内，纵向制动使峰值减速度降 31.5%，横向避让降 91.0%，并把联合 RMS jerk 降至 0.57 m/s3。按 ISO 水平频率加权，横向避让的 av,h 为 0.53 m/s2，低于反应式和纵向制动，落入较舒适区间。作者指出横向避让在安全与舒适上最优，但结果基于仿真与车辆级加速度，仍需多场景和座椅振动测量验证。
为什么重要 用知识图谱嵌入+贝叶斯推理提前3-4秒预测换道，量化纵向/横向决策的减速度与舒适性收益，为预测性自动驾驶决策提供实证。
预测周围车辆的变道意图使自动驾驶车辆能够预判潜在危险并主动响应，而不是仅依赖反应式操作。本研究探讨了将基于知识图谱嵌入和贝叶斯推断的变道预测集成到自动驾驶车辆决策中的益处。在 CARLA 模拟的危险汇入场景中评估了三种驾驶策略：反应式驾驶、基于预测的纵向动作和基于预测的横向动作。所提出的预测模型在周围车辆变道发生前约 3-4 秒预测其变道，使自车能够相应调整其行为。
在代表性模拟记录中，反应式驾驶导致碰撞，并伴随剧烈减速。相比之下，基于预测的纵向动作启动早期制动以建立安全间距，而基于预测的横向动作在存在安全相邻车道时执行变道。两种预测策略在评估记录中均避免了碰撞。与反应式驾驶相比，采用纵向动作时碰撞前峰值减速度降低了 31.5%，采用横向动作时降低了 91.0%。此外，使用了基于 ISO 2631-1 的水平振动估计来提供乘坐舒适性评估。
总体而言，结果凸显了变道预测通过主动决策支持更安全、更平稳驾驶的潜力，并且基于振动的估计为乘坐舒适性提供了额外见解。
Predicting surrounding vehicles' lane-change intentions enables autonomous vehicles to anticipate potential hazards and respond proactively rather than relying solely on reactive maneuvers.
This study investigates the benefits of integrating lane-change prediction, based on knowledge graph embeddings and Bayesian inference, into autonomous vehicle decision-making.
Three driving strategies are evaluated in risky merging scenarios simulated in CARLA: reactive driving, prediction-based longitudinal action, and prediction-based lateral action.
The proposed prediction model anticipates the surrounding vehicle's lane change approximately 3-4 seconds before its occurrence, allowing the ego vehicle to adjust its behavior accordingly.
In the representative simulation records, reactive driving results in a collision accompanied by aggressive deceleration.
In contrast, prediction-based longitudinal action initiates early braking to establish a safe gap, while prediction-based lateral action performs a lane change when a safe adjacent lane is available.
Both predictive strategies avoid collisions in the evaluated records.
Compared with reactive driving, peak deceleration before impact is reduced by 31.5% with longitudinal action and 91.0% with lateral action.
Additionally, an ISO 2631-1-based horizontal vibration estimate is used to provide a ride comfort assessment.
Overall, the results highlight the potential of lane-change prediction to support safer and smoother driving through proactive decision-making, with additional insights into ride comfort provided by vibration-based estimates.
原版排版与图表 · 手机无法内嵌时可在浏览器打开。PDF 插件内选文不能传给网页助手。