# US 8,660,699 B2 · Behavior control system and robot > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 8,660,699 B2 - Document ID: US8660699B2 - Status: Granted - Kind: B2 - Application number: 12/971,613 - Filed: 2010-12-17 - Published: 2011-06-30 - Granted: 2014-02-25 - Earliest claimed: 2009-12-24 - Assignees: Honda Motor Co., Ltd. - Applicants: Soshi Iba - Inventors: Soshi Iba - Web page: https://patentgrep.com/patent/US8660699B2 ## CPC - B25J 9/1679: {characterised by the tasks executed} - G05B 2219/39219: Trajectory tracking - G05B 2219/40026: Juggling, tennis playing, throw and catch - B25J: MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES ({manipulators specially adapted for use in surgery A61B34/70; manipulators used in cleaning hollow articles B08B9/04}; manipulators associated with rolling mills B21B39/20; manipulators associated with forging machines B21J13/10; {manipulators associated with picking-up and placing mechanisms B23P19/007}; means for holding wheels or parts thereof B60B30/00; {vehicles with ground-engaging propulsion means, e.g. walking members B62D57/02, B62D57/032; devices for picking-up and depositing articles or materials between conveyors B65G47/90, B65G47/91; manipulators with gripping or holding means for transferring packages B65H67/065}; cranes B66C; {manipulators used in the protection or supervision of pipe-line installations F17D5/00; walking equipment adapted for nuclear steam-generators F22B37/006}; manipulators specially adapted for, or associated with, nuclear reactors G21C; {apparatus used for handling wafers during manufacture or treatment of semiconductor H10P72/50}) - G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G) ## Abstract A behavior control system capable of controlling the behavior of an agent (robot) such that the agent securely applies a force to a moving object. The behavior control system calculates the degree of overlapping of a time-series probability density distribution between a predicted position trajectory of an object (ball) and a position trajectory candidate of a counter object (racket). Further, a behavior plan of the agent (robot) is generated such that the counter object is moved according to a desired position trajectory, which is a mean position trajectory or a central position trajectory of a position trajectory candidate of the counter object which has the highest degree of overlapping with the predicted position trajectory of the object among a plurality of position trajectory candidates of the counter object. ## Claims ### Claim 1 A behavior control system which controls the behavior of an agent according to a behavior plan, the behavior control system comprising an electronic control unit, and the electronic control unit comprising: a first arithmetic processing element configured to determine a predicted position trajectory of an object expressed by a probability density distribution of time-series predicted positions of the object in the future on the basis of time-series measured positions or estimated positions of the object; a second arithmetic processing element configured to generate a position trajectory candidate of a counter object expressed by a probability density distribution which indicates likelihoods corresponding to time-series positions of a counter object which includes a position coinciding, in a spatial and time-series manner, with an interaction point candidate included in the predicted position trajectory of the object in a range reachable by the counter object by a motion of the agent; and a third arithmetic processing element configured to generate a behavior plan such that a position trajectory of the counter object coincides with a desired position trajectory of the counter object, which is a mean position trajectory or a central position trajectory of one position trajectory candidate selected from among a plurality of position trajectory candidates of the counter object on the basis of the degree of overlapping of a time-series probability density distribution with the predicted position trajectory of the object. ### Claim 2 (depends on 1) The behavior control system according to claim 1, wherein the third arithmetic processing element is configured to select, from among the plurality of position trajectory candidates of the counter object, the one position trajectory candidate whose degree of overlapping of the time-series probability density distribution with the predicted position trajectory of the object is the highest or the lowest. ### Claim 3 (depends on 1) The behavior control system according to claim 1, wherein the second arithmetic processing element is configured to further determine a post-interaction predicted position trajectory of the object expressed by the probability density distribution of the time-series predicted position of the object in the case where it is assumed that the counter object interacts with the object at the interaction point candidate on the basis of the predicted position trajectory of the object and each of the plurality of position trajectory candidates of the counter object, and the third arithmetic processing element is configured to select the one position trajectory candidate from among the plurality of position trajectory candidates of the counter object on the basis of the degree of overlapping of the time-series probability density distribution between a post-interaction predicted position trajectory of the object and a specified position trajectory in addition to the degree of overlapping of the time-series probability density distribution with the predicted position trajectory of the object. ### Claim 4 (depends on 3) The behavior control system according to claim 3, wherein the third arithmetic processing element is configured to select, from among the plurality of position trajectory candidates of the counter object, the one position trajectory candidate whose total degree of overlapping of the degree of overlapping of the time-series probability density distribution with the predicted position trajectory of the object and the degree of overlapping of the time-series probability density distribution between the post-interaction predicted position trajectory of the object and the specified position trajectory is the highest or the lowest. ### Claim 5 (depends on 1) The behavior control system according to claim 1, wherein the second arithmetic processing element is configured to generate a position trajectory candidate of the counter object such that the spread of the probability density distribution indicating a likelihood associated with the position of the counter object which agrees with the interaction point candidate in the spatial and time series manner is smaller than the spread of a probability density distribution indicating a likelihood associated with another position. ### Claim 6 (depends on 1) The behavior control system according to claim 1, wherein the third arithmetic processing element is configured to calculate the degree of overlapping, excluding a time point that coincides with the interaction point candidate in the time series manner. ### Claim 7 (depends on 1) The behavior control system according to claim 1, wherein the third arithmetic processing element is configured to add a spread based on a standard deviation of the probability density distribution of the position trajectory candidate of the counter object to each of probability density distribution groups of the position trajectory candidate, and then to calculate the degree of overlapping. ### Claim 8 (depends on 1) The behavior control system according to claim 1, wherein the second arithmetic processing element is configured to generate a position trajectory candidate of the counter object according to a stochastic transition model in which the position of the counter object and a first order to an n-th order temporal differential value (n=1, 2, . . .) thereof continuously change according to a factor which indicates the shape property of an exemplary position trajectory of the position of the counter object. ### Claim 9 (depends on 8) The behavior control system according to claim 8, wherein the second arithmetic processing element is configured to generate an estimated position trajectory in the forward direction represented by the probability density distribution of an estimated position of the counter object in the forward direction time-series-wise according to the stochastic transition model, to generate an estimated position trajectory in the reverse direction represented by the probability density distribution of an estimated position of the counter object in the reverse direction time-series-wise, and then to combine, in the time series manner, the probability density distributions of the estimated position trajectory in the forward direction and the estimated position trajectory in the reverse direction, thereby generating a position trajectory candidate of the counter object expressed by the time-series combination result of the probability density distributions. ### Claim 10 (depends on 8) The behavior control system according to claim 8, wherein the second arithmetic processing element is configured to adopt a first factor defined for effecting the interaction between the counter object and the object as the factor before the interaction point candidate time-series-wise, and to generate a position trajectory candidate of the counter object according to the stochastic transition model in which a second factor, which is different from the first factor, is adopted as the factor after the interaction point candidate time-series-wise. ### Claim 11 A robot acting as an agent which has an actuator and a behavior control system and which is constructed such that the behavior thereof is controlled by controlling the operation of the actuator by the behavior control system, wherein the behavior control system comprises an electronic control unit, and the electronic control unit comprises: a first arithmetic processing element configured to determine a predicted position trajectory of an object expressed by a probability density distribution of time-series predicted positions of the object in the future on the basis of time-series measured positions or estimated positions of the object; a second arithmetic processing element configured to generate a position trajectory candidate of a counter object expressed by a probability density distribution which indicates likelihoods corresponding to time-series positions of a counter object which includes a position coinciding, in a spatial and time-series manner, with an interaction point candidate included in the predicted position trajectory of the object in a range reachable by the counter object by a motion of the agent; and a third arithmetic processing element configured to generate the behavior plan such that a position trajectory of the counter object coincides with a desired position trajectory of the counter object, which is a mean position trajectory or a central position trajectory of one position trajectory candidate selected from among a plurality of position trajectory candidates of the counter object on the basis of the degree of overlapping of a time-series probability density distribution with the predicted position trajectory of the object. ### Claim 12 (depends on 1) The behavior control system according to claim 1, wherein the third arithmetic processing element is configured to add a spread based on a variance of the probability density distribution of the position trajectory candidate of the counter object to each of probability density distribution groups of the position trajectory candidate, and then to calculate the degree of overlapping. ### Claim 13 (depends on 1) The behavior control system according to claim 1, wherein the third arithmetic processing element is configured to correct a spread of each of the probability density distribution groups of the position trajectory candidate to a spread based on a standard deviation of the probability density distribution of the position trajectory candidate of the counter object, and then to calculate the degree of overlapping. ### Claim 14 (depends on 1) The behavior control system according to claim 1, wherein the third arithmetic processing element is configured to correct a spread of each of the probability density distribution groups of the position trajectory candidate to a spread based on a variance of the probability density distribution of the position trajectory candidate of the counter object, and then to calculate the degree of overlapping.