The present invention proposes an active scene mapping method based on constraint guidance and space optimization strategies, comprising a global planning stage and a local planning stage; in the global planning stage, the next exploration goal of a robot is calculated to guide the robot to explore a scene; and after the next exploration goal is determined, specific actions are generated according to the next exploration goal, the position of the robot and the constructed occupancy map in the local planning stage to drive the robot to go to a next exploration goal, and observation data is collected to update the information of the occupancy map. The present invention can effectively avoid long-distance round trips in the exploration process so that the robot can take account of information gain and movement loss in the exploration process, find a balance of exploration efficiency, and realize the improvement of active mapping efficiency.

This document describes motion planning with variable grid resolution for graph-search-based planning. An example system includes a processor that obtains an initial pose, a goal pose, and an obstacle map for an environment. The processor uses a motion-planning algorithm to determine a path or trajectory using two or more grid resolutions for a graph-based search. The path includes a series of waypoints, including two-dimensional positional coordinates (and time coordinates if a trajectory), to navigate from the initial pose towards the goal pose. Operation of the host vehicle is then controlled to maneuver along the path using an assisted-driving or autonomous-driving system. In this way, motion planning is performed for the entire path but uses a coarser grid resolution for the portion nearer the goal pose. This allows motion planning for autonomous parking, especially in environments that include static and dynamic objects, to be handled in a more computationally-efficient manner.

A control device includes a recognition part that recognizes a position of an object present around a moving body based on an image obtained by imaging a state around the moving body, an occupancy grid diagram generation part that generates an occupancy grid diagram including a plurality of grid cells based on the position of the object present around the moving body, and a route generation part that generates a route, which the moving body follows, based on the occupancy grid diagram, and the occupancy grid diagram generation part determines whether the object is present for each of the plurality of grid cells in the occupancy grid diagram based on the position of the object present around the moving body, and the occupancy grid diagram generation part expands a first region including a grid cell in which it is determined that the object is present.

A control device includes recognition-part that recognizes position of object present around moving-body based on image obtained by imaging state around the moving-body, occupancy-grid-diagram-generation-part that generates occupancy grid diagram including a plurality of grid cells based on the position of the object present around the moving-body, and route generation part that generates a route, which the moving-body follows based on contour of the object shown in the occupancy grid diagram, and the occupancy-grid-diagram-generation-part determines whether the object is present for each of the plurality of grid cells in the occupancy grid diagram based on the position of the object present around the moving-body, generates first contour showing contour of first region including grid cell in which it is determined that the object is present, and generates second contour including the first region with apex number smaller than that of the first contour as the contour of the object.

An indoor mobile industrial robot system is configured to provide a weight to a detected object within an operating environment, where the weight relates to how static the feature is. The indoor mobile industrial robot system includes a mechanism configured to translate reflected light energy and positional information into a set of data points representing the detected object having at least one of Cartesian and/or polar coordinates, and an intensity. If any discrete data point within the set of data points representing the detected object has an intensity at or above a defined threshold the entire set of data points is converted into a weight and potentially classified representing a static feature, otherwise such set of data points is classified as representing a dynamic feature having a lower weight.

There are provided a device and a method capable of reducing the processing load in the safety confirmation of the sub-goal and improving the possibility of detecting the safe traveling route. A sub-goal generation unit that generates a sub-goal pattern including a plurality of sub-goals in a traveling direction of a mobile object; and a sub-goal safety verification unit that performs safety verification as to whether or not the mobile object can safely travel, on each of the sub-goals constituting the sub-goal pattern are provided. The sub-goal generation unit generates a coarse sub-goal pattern having a wide sub-goal interval and a dense sub-goal pattern having a narrow sub-goal interval. The sub-goal safety verification unit performs the safety verification on the sub-goals of the coarse sub-goal pattern, and in a case where the sub-goal enabling the safe traveling is not detected, the sub-goal safety verification unit executes the safety verification on each of the sub-goals of the dense sub-goal pattern.

The invention is notably directed to a method of driving an automated vehicle (10) comprising a drive-by-wire (DbW) system (300) with electromechanical actuators. The method is performed by a validation unit (220), which is connected to a motion planning unit (106). The validation unit and the motion planning unit may form part of the vehicle, making it an autonomous vehicle. In variants, the validation unit and the motion planning unit form part of a central control unit, which, e.g., remotely steers the vehicle in a designated area. The method and revolves around receiving (S10) provisional commands and accordingly triggering (S70-S90) an actuation sequence. The provisional commands are received (S10) from the motion planning unit (106). The provisional commands contain provisional instructions with respective execution times. The provisional commands are designed to be executed by respective ones of the electromechanical actuators to cause the vehicle (10) to follow a drivable trajectory. The actuation sequence is triggered (S70-S90) by generating (S70) effective commands based on the provisional commands received and timely sending (S80) the effective commands generated to the electromechanical actuators, whereby an effective command containing an effective instruction is repeatedly generated (S70) for and sent (S80) to each actuator of said electromechanical actuators. Each effective command of at least some of the effective commands sent to said each actuator is generated (S70) by selecting (S76) provisional commands and accordingly determining (S77) the effective instruction of each effective command. That is, two or more provisional commands are selected (S76) among the provisional commands received in respect of each actuator, in accordance with an effective time point, the latter corresponding to a current time point corrected to compensate for an actuator delay of said each actuator. The effective instruction of each effective command is then determined (S77) based on provisional instructions of the two or more provisional commands selected and their respective execution times. The invention is further directed to related systems and computer program products.

Techniques are provided for utilizing a dynamic occupancy grid (DoG) for tracking objects proximate to an autonomous or semi-autonomous vehicle. An example method for generating an object track list in a vehicle includes obtaining sensor information from one or more sensors on the vehicle, determining a first set of object data based at least in part on the sensor information and an object recognition process, generating a dynamic grid based on an environment proximate to the vehicle based at least in part on the sensor information, determining a second set of object data based at least in part on the dynamic grid, and outputting the object track list based on a fusion of the first set of object data and the second set of object data.

Techniques are provide for generating occupancy grids based on inputs from multiple heterogeneous sensors. An example method for generating an occupancy grid includes obtaining detection information from a plurality of heterogeneous sensors, generating a single measurement grid based on the detection information from the plurality of heterogeneous sensors, determining occupancy probabilities for a plurality of cells in the single measurement grid, and outputting the occupancy grid based at least in part on the occupancy probabilities.

The invention is notably directed to a control system for steering an automated vehicle in a designated area, where the automated vehicle comprises a drive-by-wire (DbW) system. The control system includes a set of perception sensors (e.g., lidars, cameras, as well as radars, sonars, GPS, and inertial measurement units), which are arranged in a designated area. The control system further includes a control unit, which is in communication with the perception sensors and the DbW system, and which comprises two processing systems, i.e., a first processing system and a second processing system, which are in communication with each other. The first processing system is configured to form a main perception based on signals from each of the perception sensors of the set, estimate states of the vehicle based on feedback signals from the DbW system, and compute trajectories for the automated vehicle based on the main perception formed and the estimated states. The second processing system is configured to form an auxiliary perception based on signals from only a subset of the perception sensors, validate the computed trajectories based on the auxiliary perception formed, and cause the control unit to forward the validated trajectories to the DbW system of the automated vehicle. This way, the vehicle can be remotely steered through the DbW system based on the validated trajectories forwarded to the DbW system. In other words, distinct perceptions are formed from overlapping sets of sensors, whereby one of the perceptions formed is used to validate trajectories obtained from the other. This requires less computational efforts, inasmuch as less signals (and therefore less information) are required to form the auxiliary perception. However, doing so is more likely to allow inconsistencies to be detected, thanks to the heterogeneity of sensor signals considered in input to the main and auxiliary perceptions. The invention is further directed to related methods and computer program products.