Abstract:
A state where at least a part of the virtual object (e.g., a foot of a robot) enters into the actual object (e.g., floor), i.e., a state where at least a part of a plurality of virtual points located on the surface of the virtual object is inside the actual object, can be assumed. At each of the inside and the outside of the actual object, as a virtual point is located at a deeper position inside and away from the surface or the skin part of the actual object and as a coordinate value difference ΔZi is larger, a higher value is calculated for the cost Ei as well. The combination Z^ of coordinate values of virtual points, bringing the total cost E=ΣiEi closer to an absolute minimum or a local minimum, can be searched.
Abstract:
A controller for a mobile robot which carries out task of moving an object so as to make a position of a representative point of the object and a posture of the object follow a desired position trajectory and a desired posture trajectory, in a state where distal portions of arms is made to contact a portion adjacent to one end of the object, which variably sets the position of the representative point of the object in an object coordinate system when the object is observed in the yaw axis direction, at least in accordance with the change of the desired posture about the yaw axis in the desired posture trajectory. By doing so, movement of the object appropriate for the changing pattern of the desired posture of the object is carried out.
Abstract:
A mobile apparatus and a localization method thereof which perform localization of the mobile apparatus using a distributed filter system including a plurality of local filters independently operated and one fusion filter integrating results of localization performed through the respective local filters, and additionally apply accurate topological absolute position information to the distributed filter system to improve localization performance (accuracy, convergence and speed in localization, etc.) of the mobile apparatus on a wide space. The mobile apparatus includes at least one sensor, at least one first distribution filter generating current relative position information using a value detected by the at least one sensor, at least one second distribution filter generating current absolute position information using the value detected by the at least one sensor, and a fusion filter integrating the relative position information and the absolute position information to perform localization.
Abstract:
A target route generation system which generates a target route for a robot (R) to travel along autonomously is provided with a route candidate generation element (110) which generates a plurality of travel route candidates to connect the terminating point and the starting point by connecting links stored at a link storing element (211), state recognition elements (115 to 118) which recognize a state of the robot (R), and a route evaluation IC element (120) which evaluates a cost of a travel route candidate including therein an action point stored in an action point storing element (212) lower as the necessity for passing by the action point is higher in view of the state of the robot (R) recognized by the state recognition elements (115 to 118). According to the system, the robot can be made to travel through the action point with a high necessity in view of the state of the robot.
Abstract:
A state where at least a part of the virtual object (e.g., a foot of a robot) enters into the actual object (e.g., floor), i.e., a state where at least a part of a plurality of virtual points located on the surface of the virtual object is inside the actual object, can be assumed. At each of the inside and the outside of the actual object, as a virtual point is located at a deeper position inside and away from the surface or the skin part of the actual object and as a coordinate value difference ΔZi is larger, a higher value is calculated for the cost Ei as well. The combination Ẑ of coordinate values of virtual points, bringing the total cost E=ΣiEi closer to an absolute minimum or a local minimum, can be searched.
Abstract:
In an environment recognition apparatus including a light projector that intermittently projects a light pattern toward an object to be measured existing in an environmental space in accordance with a duty factor of a pulse train defining one frame, a camera that outputs a difference image between an image of the object taken at an exposure where the light pattern is projected and an image of the object taken at an exposure where the light pattern is not projected and the object is recognized based on the difference image, there is equipped with a timing controller that controls the projection timing by varying a pulse repetition period in the pulse train in one frame at random, thereby effectively avoiding the interference with the other while using a camera of ordinary sensitivity.
Abstract:
Even when a first moving condition is not satisfied, when it is determined that a second moving condition is satisfied and at the same time an object belongs to a second classification, an operation of a robot is controlled so as to prompt the object to move according to a first pattern or an arbitrary pattern. The “first moving condition” is a condition that the robot is capable of moving without being obstructed by the object when the robot moves according to a current target position trajectory. The “second moving condition” is a condition that the robot is capable of moving according to the current target position trajectory without being obstructed by the object when the object is displaced according to the first pattern. The “second classification” means a classification of the object which is capable of being moved by a force from the robot acting thereon.
Abstract:
A suitable waypoint is selected using a goal score, a section from a start point to a goal point through the waypoint is divided into a plurality of sections based on the waypoint with a solution of inverse kinematics, and trees are simultaneously expanded in the sections using a Best First Search & Rapidly Random Tree (BF-RRT) algorithm so as to generate a path. By this configuration, a probability of local minima occurring is decreased compared with the case where the waypoint is randomly selected. In addition, since the trees are simultaneously expanded in the sections each having the waypoint with a solution of inverse kinematics, the solution may be rapidly obtained. A time consumed to search for an optimal motion path may be shortened and path plan performance may be improved.
Abstract:
If a manipulator of a robot falls in local minima when expanding a node to generate a path, the manipulator may efficiently escape from local minima by any one of a random escaping method and a goal function changing method or a combination thereof to generate the path. When the solution of inverse kinematics is not obtained due to local minima or when the solution of inverse kinematics is not obtained due to an inaccurate goal function, an optimal motion path to avoid an obstacle may be efficiently searched for. The speed to obtain the solution may be increased and thus the time consumed to search for the optimal motion path may be shortened.
Abstract:
The present invention provides an obstacle avoiding apparatus, an obstacle avoiding method, an obstacle avoiding program, and a mobile robot apparatus that can accurately model a robot apparatus and plan a highly precise moving route for the robot apparatus that avoids obstacles. The obstacle avoiding apparatus, to be used for a mobile robot apparatus to avoid obstacles, includes an obstacle environment map drawing section that divides the range of height from the reference surface for the mobile robot apparatus to move thereon to the height of the mobile robot apparatus into a plurality of layers corresponding to predetermined respective ranges of height and draws obstacle environment maps, each showing the condition of being occupied by one or more than one obstacles existing in the corresponding layer, and a route planning section that plans a route for the robot apparatus to move along according to an enlarged environment map prepared by enlarging the area occupied by the obstacle or obstacles in the obstacle environment maps as a function of the cross sectional profile of the mobile robot apparatus in each of the layers.