Baidu USA LLC

Jiacheng Pan

Hongyi Sun

Jinghao Miao

Kecheng Xu

Jiangtao Hu

Yifei Jiang

Jiaming Tao

Yajia Zhang

Jinyun Zhou

Jiaxuan Xu

Shu Jiang

Xiangquan Xiao

Qi Luo

Haoyang Fan

In one embodiment, a process is performed during controlling Autonomous Driving Vehicle (ADV). A confidence level associated with a sensed obstacle is determined. If the confidence level is below a confidence threshold, and a distance between the ADV and a potential point of contact with the sensed obstacle is below a distance threshold, then performance of a driving decision is delayed. Otherwise, the driving decision is performed to reduce risk of contact with the sensed obstacle.

Delay decision making for autonomous driving vehicles in response to obstacles based on confidence level and distance

An obstacle state evolution of a spatial position of a moving obstacle over a period of time is determined. A lane-obstacle relation evolution of the moving obstacle with each of one or more lanes near the moving obstacle over the period of time is further determined. An intended movement of the moving obstacle is predicted based on the obstacle state evolution and the lane-obstacle evolution. Thereafter, a trajectory of the ADV is planned to control the ADV to avoid a collision with the moving obstacle based on the predicted intended movement of the moving obstacle. The above process is iteratively performed for each of the moving obstacles detected within a predetermined proximity of the ADV.

Lane-attention: predicting vehicles' moving trajectories by learning their attention over lanes

According to one embodiment, during a first planning cycle, a first lane boundary of a driving environment perceived by an ADV is determined using a first lane boundary determination scheme (e.g., current lane boundary), which has been designated as a current lane boundary determination scheme. A first trajectory is planned based on the first lane boundary to drive the ADV to navigate through the driving environment. The first trajectory is evaluated against a predetermined set of safety rules (e.g., whether it will collide or get too close to an object) to avoid a collision with an object detected in the driving environment. In response to determining that the first trajectory fails to satisfy the safety rules, a second lane determination boundary of the driving environment is determined using a second lane boundary determination scheme and a second trajectory is planned based on the second lane boundary to drive the ADV.

Hierarchical path decision system for planning a path for an autonomous driving vehicle

In one embodiment, an autonomous driving system of an ADV perceives a driving environment surrounding the ADV based on sensor data obtained from various sensors, including detecting one or more lanes and at least a moving obstacle or moving object. For each of the lanes identified, an NN lane feature encoder is applied to the lane information of the lane to extract a set of lane features. For a given moving obstacle, an NN obstacle feature encoder is applied to the obstacle information of the obstacle to extract a set of obstacle features. Thereafter, a lane selection predictive model is applied to the lane features of each lane and the obstacle features of the moving obstacle to predict which of the lanes the moving obstacle intends to select.

Neural network with lane aggregation for lane selection prediction of moving objects during autonomous driving

A moving obstacle such as a vehicle within a proximity of an intersection and one or more exits of the intersection are identified. An obstacle state evolution of a spatial position of the moving obstacle over a period of time is determined. For each of the exits, an intersection exit encoding of the exit is determined based on intersection exit features of the exit. An aggregated exit encoding based on aggregating all of the intersection exit encodings for the exits is determined. For each of the exits, an exit probability of the exit that the moving obstacle likely exits the intersection through the exit is determined based on the obstacle state evolution and the aggregated exit encoding. Thereafter, a trajectory of the ADV is planned to control the ADV to avoid a collision with the moving obstacle based on the exit probabilities of the exits.

Method for predicting exiting intersection of moving obstacles for autonomous driving vehicles

In response to perceiving a moving object, one or more possible object paths of the moving object are determined based on the prior movement predictions of the moving object, for example, using a machine-learning model, which may be created based on a large amount of driving statistics of different vehicles. For each of the possible object paths, a set of trajectory candidates is generated based on a set of predetermined accelerations. Each of the trajectory candidates corresponds to one of the predetermined accelerations. A trajectory cost is calculated for each of the trajectory candidates using a predetermined cost function. One of the trajectory candidates having the lowest trajectory cost amongst the trajectory candidates is selected. An ADV path is planned to navigate the ADV to avoid collision with the moving object based on the lowest costs of the possible object paths of the moving object.

Method for predicting movement of moving objects relative to an autonomous driving vehicle

In one embodiment, a set of predetermined driving parameters is determined from a set of driving statistics data collected from a number of vehicles, which may be driven by human drivers. For each pair of the predetermined driving parameters, a distribution of the pair of driving parameters is plotted based on their relationship on a two-dimensional (2D) distribution space. The 2D distribution space is partitioned into a number of grid cells, each grid cell representing a particular pair of driving parameters. For each of the grid cells, a probability is calculated that the pair of driving parameter likely falls in the grid cell. A grid table is generated corresponding to the pair of driving parameters. The grid table can be utilized during the autonomous driving at real-time or during simulation to determine a ride stability of an autonomous driving vehicle (ADV) in view of the pair of driving parameters.

Method for determining ride stability of an autonomous driving system controlling an autonomous driving vehicle

A moving object such as a vehicle is identified within an intersection having multiple exits. The moving object and the intersection and its exits may be identified based on sensor data obtained from various sensors mounted on an ADV. An exit coordinate map is generated based on the orientation of the moving object and a relative position of each of the exits of the intersection with respect to the current position of the moving object. For each of the exits, an exit probability of the exit that the moving object likely exits the intersection using the exit coordinate map. Thereafter, a trajectory of the ADV is planned to navigate through the intersection to avoid the collision with the moving object based on the exit probabilities of the exits of the intersection. The above process is iteratively performed for each of the moving objects detected within the proximity of the intersection.

Method for determining exiting intersection of moving objects for autonomous driving vehicles

A system and method for predicting the near-term trajectory of a moving obstacle sensed by an autonomous driving vehicle (ADV) is disclosed. The method applies neural networks such as a LSTM model to learn dynamic features of the moving obstacle's motion based on its past trajectory up to its current position and a CNN model to learn the semantic map features of the driving environment in a portion of an image map. From the learned dynamic features of the moving obstacle and the learned semantic map features of the environment, the method applies a neural network to iteratively predict the moving obstacle's positions for successive time points of a prediction interval. To predict the moving obstacle's position at the next time point from the currently predicted position, the methods may update the learned dynamic features of the moving obstacle based on its past trajectory up to the currently predicted position.

Vehicle trajectory prediction model with semantic map and LSTM

A driving environment is perceived based on sensor data obtained from a plurality of sensors mounted on the ADV. In response to a request for changing lane from a first lane to a second lane, path planning is performed. The path planning includes identifying a first lane change point for the ADV to change from the first lane to the second lane in a first trajectory of the ADV, determining a lane change preparation distance with respect to the first lane change point, and generating a second trajectory based on the lane change preparation distance, where the second trajectory having a second lane change point delayed from the first lane change point. Speed planning is performed on the second trajectory to control the ADV to change lane according to the second trajectory with different speeds at different point in time.

Path planning with a preparation distance for a lane-change

In one embodiment, a process is performed during controlling Autonomous Driving Vehicle (ADV). A plurality of point confidence scores are determined, each defining a reliability of a corresponding point on a trajectory of a moving obstacle. At least one of the point confidence scores is determined based on a) an overall trajectory confidence score, and b) at least one environmental factor of the obstacle. The ADV is controlled based on the trajectory of the moving obstacle and at least one of the plurality of point confidence scores.

Confidence levels along the same predicted trajectory of an obstacle

In one embodiment, a data processing system for an autonomous driving vehicle (ADV) includes a processor, and a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations. The operations include generating a station-time (ST) graph based on perception data obtained from one or more sensors of the ADV, the ST graph including representing a location of an obstacle at different points in time, obtaining a tensor based on the ST graph, the tensor including a plurality of layers, the plurality of layers including a first layer having data representing one or more obstacles on a path in which the ADV is moving, applying a machine-learning model to the plurality of layers of the tensor to generate a plurality of numerical values, the plurality of numerical values defining a potential path trajectory of the ADV, and determining a path trajectory of the ADV based on the plurality of numerical values.

Growing community of inventors

Sunnyvale, CA, United States of America

Jiacheng Pan