Method for ascertaining potential trajectories when controlling a robot device

A method for controlling a robot device, the method comprising the following steps:

• ascertaining a plurality of potential trajectories of an object in a surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each potential trajectory of the one or more potential trajectories, a weighting factor assigned to the trajectory;
• ascertaining a plurality of weighted similarity values by ascertaining a respective weighted similarity value for each potential trajectory of the plurality of potential trajectories, wherein the ascertaining of the respective weighted similarity value for a potential trajectory includes:
• ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to one or more similarity metrics, and
• ascertaining the respective weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory;
• summing the plurality of weighted similarity values to produce an error value;
• adapting the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced error value;
• generating control parameters for controlling the robot device using the adapted set of proposed trajectories;
• and
• controlling the robot device according to the control parameters.

A control device configured to control a robot device, the control device configured to:

• ascertain a plurality of potential trajectories of an object in a surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each potential trajectory of the one or more potential trajectories, a weighting factor assigned to the trajectory;
• ascertain a plurality of weighted similarity values by ascertaining a respective weighted similarity value for each potential trajectory of the plurality of potential trajectories, wherein the ascertaining of the respective weighted similarity value for a potential trajectory includes:
• ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to one or more similarity metrics, and
• ascertaining the respective weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory;
• sum the plurality of weighted similarity values to produce an error value;
• adapt the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced error value;
• generate control parameters for controlling the robot device using the adapted set of proposed trajectories;
• and
• control the robot device according to the control parameters.

A robot device, comprising:

• a control device configured to control the robot device, the control device configured to:
• ascertain a plurality of potential trajectories of an object in a surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each potential trajectory of the one or more potential trajectories, a weighting factor assigned to the trajectory;
• ascertain a plurality of weighted similarity values by ascertaining a respective weighted similarity value for each potential trajectory of the plurality of potential trajectories, wherein the ascertaining of the respective weighted similarity value for a potential trajectory includes:
• ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to one or more similarity metrics, and
• ascertaining the respective weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory;
• sum the plurality of weighted similarity values to produce an error value;
• adapt the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced error value;
• generate control parameters for controlling the robot device using the adapted set of proposed trajectories;
• and
• control the robot device according to the control parameters.

A non-transitory computer-readable medium in which is stored commands for controlling a robot device, the command, when executed by a processor, causing the processor to perform the following steps:

• ascertaining a plurality of potential trajectories of an object in a surrounding area of the robot device by ascertaining in each case one or more potential trajectories using one or more machine learning models and, for each potential trajectory of the one or more potential trajectories, a weighting factor assigned to the trajectory;
• ascertaining a plurality of weighted similarity values by ascertaining a respective weighted similarity value for each potential trajectory of the plurality of potential trajectories, wherein the ascertaining of the respective weighted similarity value for a potential trajectory includes:
• ascertaining a similarity value that represents a similarity between the potential trajectory and a set of proposed trajectories according to one or more similarity metrics, and
• ascertaining the respective weighted similarity value by weighting the similarity value according to the weighting factor assigned to the potential trajectory;
• summing the plurality of weighted similarity values to produce an error value;
• adapting the set of proposed trajectories to ascertain an adapted set of proposed trajectories that results in a reduced error value;
• generating control parameters for controlling the robot device using the adapted set of proposed trajectories;
• and
• controlling the robot device according to the control parameters.