摘要：【中文】本发明公开了一种基于改进人工势场的智能车辆轨迹规划方法，包括：获取智能车辆信息、障碍物信息、道路边界信息；确定目标点位置；建立道路直角坐标系以及车辆等效模型，以及建立智能车与道路的碰撞约束条件；根据智能车辆信息、障碍物信息以及目标点位置建立障碍物斥力势场和目标引力势场；根据智能车辆在所有障碍物斥力势场和目标点引力势场组成的复合场中所受到的力的作用，建立智能车辆的平衡方程；求解上述平衡方程，得到一系列点的坐标，将这些点用一条平滑的曲线连接起来，以得到一条智能车辆在规划周期内安全可行的行驶轨迹。本发明有效的避开静止障碍物和动态车辆障碍物，更快的向目标靠近，从而得到一条安全可行的最优轨迹。 【EN】The invention discloses an intelligent vehicle track planning method based on an improved artificial potential field, which comprises the following steps: acquiring intelligent vehicle information, obstacle information and road boundary information; determining the position of a target point; establishing a road rectangular coordinate system and a vehicle equivalent model, and establishing a collision constraint condition of the intelligent vehicle and the road; establishing an obstacle repulsive force potential field and a target attractive force potential field according to the intelligent vehicle information, the obstacle information and the target point position; establishing a balance equation of the intelligent vehicle according to the action of force applied to the intelligent vehicle in a composite field consisting of the repulsive force fields of all obstacles and the attractive force fields of the target points; and solving the balance equation to obtain coordinates of a series of points, and connecting the points by using a smooth curve to obtain a safe and feasible driving track of the intelligent vehicle in a planning period. The invention effectively avoids static obstacles and dynamic vehicle obstacles and approaches to the target more quickly, thereby obtaining a safe and feasible optimal track.

摘要：【中文】本发明公开了一种基于规则的智能网联车辆协同汇入控制方法，包括主干道外侧车道车辆与匝道车辆建立通信并传输车辆的状态量；定义车辆协同规则；预测主干道外侧车道车辆和匝道车辆到汇入口处所需时间；根据预测的结果决策主干道外侧车道车辆是否需要换道、加速、减速来进行避让，或匝道车辆是否需要加速、减速来进行避让，得到一个车辆能够安全通过汇入口处的方案；车辆按决策方案行驶。本发明的方法以燃油经济性和通行效率为目标，通过主干道外侧车道车辆的换道避让、主干道和匝道车辆的加减速避让，实现了智能网联车辆的协同汇入控制。 【EN】The invention discloses an intelligent networking vehicle cooperative convergence control method based on rules, which comprises the steps of establishing communication between vehicles on a lane outside a main road and vehicles on a ramp and transmitting the state quantity of the vehicles; defining a vehicle cooperation rule; predicting the time required by the vehicles on the outer lane of the main road and the vehicles on the ramp to the junction; according to the prediction result, whether vehicles on the lane outside the main road need to change lanes, accelerate and decelerate to avoid or whether vehicles on the ramp need to accelerate and decelerate to avoid is determined, and a scheme that the vehicles can safely pass through the junction is obtained; and the vehicle runs according to the decision scheme. The method of the invention aims at fuel economy and traffic efficiency, and realizes the cooperative entry control of the intelligent networked vehicles through lane change avoidance of vehicles on the outer side of the main road and acceleration and deceleration avoidance of vehicles on the main road and the ramp.

摘要：【中文】本发明公开了一种基于模型切换及融合的荷电状态估计方法，用于提高动力电池SOC估计的准确性，当电动汽车或者电动水下航行器长时间工作时，根据电池管理系统采集到的温度和压强信息得到切换时间t_s作为切换动作执行判断的重要依据。工况前期利用Rint模型结合扩展卡尔曼滤波器对荷电状态进行估计，并作为相应时刻的最终结果；工况后期利用一阶和二阶RC模型各自得到的荷电状态估计结果进行加权融合，融合后同样作为该时刻的最终结果。并且任意时刻的最终估计结果要作为下一时刻估计的初始值，保证收敛速度。 【EN】The invention discloses a state of charge estimation method based on model switching and fusion, which is used for improving the accuracy of power battery SOC estimation_sAs an important basis for the execution judgment of the switching action. Estimating the state of charge by utilizing a Rint model in combination with an extended Kalman filter at the early stage of the working condition, and taking the estimated state of charge as a final result at a corresponding moment; and in the later stage of the working condition, weighted fusion is carried out by utilizing the charge state estimation results obtained by the first-order RC model and the second-order RC model respectively, and the fused result is also used as the final result at the moment. And the final estimation result at any time is used as the initial value of the next time estimation, so that the convergence speed is ensured.

摘要：【中文】本发明公开了一种基于模型与算法分步融合的荷电状态估计方法，用于提高动力电池SOC估计的准确性，针对实车搭载中复杂多变的各类噪声，单一滤波器往往无法保证良好的估计效果，结合AEKF和HIF各自优点能够在SOC初值不精确、电流和电流传感器的测量噪声、环境的随机干扰等恶劣情况下依然能够有较好的SOC估计精度和收敛稳定性。针对在较长运转工况下，单一模型无法保证在全程都有最佳的估计精度，结合RINT、一阶RC、二阶RC三种模型去进一步提高SOC估计精度，并且任意时刻的最终估计结果要作为下一时刻估计的初始值，保证收敛速度。 【EN】The invention discloses a state of charge estimation method based on stepwise fusion of a model and an algorithm, which is used for improving the accuracy of power battery SOC estimation, aiming at various complex and changeable noises in real vehicle carrying, a single filter often cannot ensure good estimation effect, and by combining the advantages of AEKF and HIF, the method still can have good SOC estimation accuracy and convergence stability under the severe conditions of inaccurate initial SOC value, measurement noises of current and current sensors, random interference of environment and the like. Aiming at the problem that a single model cannot guarantee the optimal estimation precision in the whole process under a long operating condition, the SOC estimation precision is further improved by combining three models, namely RINT, first-order RC and second-order RC, and the final estimation result at any moment is used as the initial value of the estimation at the next moment, so that the convergence speed is guaranteed.