1. A system comprising:
a transmitter for transmitting wireless signals in all directions within a range of directions, the range of directions including at least all directions in a plane;
a receiver for receiving echoes of the wireless signals from any direction in the range;
a processor for processing the received echoes to derive echo data signals indicative of the distance of the system to a plurality of reflective surfaces;
an adaptive system for:
during a training stage, learning at least one association between the echo data signals and the position of the system based on training data composed of records of echo data signals and associated system position data, and
during a working stage, using the echo data signals and the learnt association to determine the position of the system; and
a clustering and classifying unit, the clustering and classifying unit being arranged:
during the training stage, to partition the echo data signals of the training data into clusters, the adaptive system learning an association for each cluster between the echo data signals of that cluster and the associated positions of the system,
wherein a linear transformation between a vector of distances and two-dimensional coordinates are estimated for a corresponding cluster,
wherein the linear transformation between the distance vector and the two-dimensional coordinates are estimated for a variable amount of training points, and wherein the accuracy of the estimations is a function of a selection of the points; and
during the working stage, to determine which cluster the echo data signals belong to, whereby the adaptive system determines the position of the system using the learnt association of the corresponding cluster.
2. A system according to claim 1 in which the processor includes a distance vector determination unit for providing the echo data signals comprising numbers which indicate the distances from the system to each of a number of respective reflective surfaces.
3. A system according to claim 1 in which the processor in includes a distance vector determination unit for providing the echo data signals comprising numbers which indicate the difference of the squares of the distances of the system to a respective pair of the reflective surfaces.
4. A system according to claim 1, in which the processor is arranged to modify the relationship between the echoes and the echo data signals to generate echo data signals comprising a plurality of numbers having linear relationships to position values of the system measured relative to Cartesian axes.
5. A system according to claim 1 in which the clustering and classifying unit includes a clustering unit adapted during the training stage to derive a cluster index indicative of a cluster associated with the echo data signals, and a classifying unit arranged during the training stage to learn associations between the echo data signals and the cluster indices and during the working phase to output a cluster index based on the echo data signals.
6. A system according to claim 5 in which the classifying unit is arranged to employ a learning vector quantization algorithm.
7. A system according to claim 6 in which the clustering unit during the training stage is arranged to take as input a vector comprising the echo data signals and the associated positions.
8. A system according to claim 6 in which the clustering unit during the training stage is arranged to take as input a vector comprising a linear transformation derived from the echo data signals and associated positions.
9. A system according to claim 1 in which the adaptive system includes at least one neural network.
10. A system according to claim 1 in which the adaptive system includes a neural network for each cluster, the neural network being trained using training data for the corresponding cluster to learn the association for echo data signals of the corresponding cluster.
11. A system according to claim 10 in which each neural network is a two-layer network.
12. A system according to claim 11 in which each neural network performs a linear function of its inputs.
13. A system according to claim 1 in which the adaptive system includes for each cluster a respective transformation unit adapted during the training stage to derive a respective linear transformation of its inputs.
14. A system according to claim 13 in which the transformation units derive the linear transformation by a least squares algorithm based on (i) vectors of distances as an input and (ii) positions associated with the echo data signals as outputs.
15. A system according to claim 1 in which the signals are RF wireless signals.
16. A system according to claim 15 in which the transmitter is an omni-directional antenna.
17. A method of determining the position of an object, the method comprising:
transmitting wireless signals from the object in all directions within a range of directions which includes at least all directions in a plane;
receiving at the object echoes of the wireless signals from any of the range of directions;
processing the received echoes to derive echo data signals indicative of the distance of the object to a plurality of reflective surfaces;
during a training stage, learning at least one association between the echo data signals and the position of the system based on echo data signals and associated object position data,
during a working stage, using the echo data signals and the learnt association to determine the position of the object; and
during the training stage, partitioning echo data signals of the training data into clusters, the adaptive system learning an association for each cluster between the echo data signals of that cluster and the associated positions of the object,
wherein a linear transformation between a distance vector and two-dimensional coordinates are estimated for a corresponding cluster,
wherein the linear transformation between the distance vector and the two-dimensional coordinates are estimated for a variable amount of training points, and wherein the accuracy of the estimations is a function of a selection of the points; and
during the working stage, determining which cluster the echo data signals belong to, whereby the adaptive system determines the position of the object using the learnt association of the corresponding cluster.
18. A method according to claim 17 in which the echo data signals comprise numbers having linear relationships to position values of the object measured relative to Cartesian axes.
19. A method according to claim 17 in which the echo data comprise signals indicate the distances from the object to each of a number of respective reflective surfaces.
20. A method according to claim 18 in which the echo data comprise signals that indicate the distances from the object to each of a number of respective reflective surfaces and in which the respective reflective surfaces are substantially planar.
21. A method according to claim 17 in which the echo data signals comprise numbers which indicate the difference of the squares of the distances of the system to a respective pair of the reflective surfaces.
22. A method according to claim 18 in which the echo data signals comprise numbers which indicate the difference of the squares of the distances of the system to a respective pair of the reflective surfaces, and in which the respective reflective surfaces are point-like reflectors.
23. A method according to claim 18 including a step of determining a transform from the echoes to the echo data signals according to the nature of the reflective surfaces.
24. A method according to claim 17 in which: during the training stage a clustering unit derives a cluster index indicative of a cluster associated with the echo data signals, and a classifying unit learns associations between the echo data signals and the cluster indices, and
during the working phase to output a cluster index based on the echo data signals.
25. A method according to claim 24 in which the classifying unit employs a learning vector quantization algorithm.
26. A method according to claim 25 in which the clustering unit takes as input a vector comprising the echo data signals and the associated positions.
27. A method according to claim 25 in which the clustering unit takes as input a vector comprising a linear transformation derived from the echo data signals and associated positions.
28. A method according to claim 17 in which the learning is at least partly performed by at least one neural network.
29. A method according to claim 17 which employs a neural network for each cluster, the neural network being trained using training data for the corresponding cluster to learn the association for echo data signals of the corresponding cluster.
30. A method according to claim 29 in which each neural network is a two layer network.
31. A method according to claim 30 in which each neural network performs a linear function of its inputs.
32. A method according to claim 17 in which the adaptive system includes for each cluster a respective transformation unit which during the training stage derives a respective linear transformation of its inputs.
33. A method according to claim 32 in which the transformation units derive the linear transformation by a least squares algorithm based on (i) vectors of distances as an input and (ii) positions associated with the echo data signals as outputs.
34. A method according to claim 17 in which the range of directions is all directions within a three-dimensional space.
The claims below are in addition to those above.
All refrences to claim(s) which appear below refer to the numbering after this setence.
1. A robot which executes a task by making autonomous actions on the basis of communication with a support server provided with a task database, comprising:
a plurality of active sensors with directivity configured to output electromagnetic waves or elastic oscillation waves, and output signals related to an external state of the robot according to the received reflection waves of the electromagnetic waves or the elastic oscillation waves; and
a controller configured to control actions of a self robot on the basis of the output signals from the plurality of active sensors;
wherein the controller is provided with a first processing element and a second processing element,
the first processing element is configured to determine a position and an orientation of the self robot,
store the position and the orientation in the task database on the basis of communication with the support server,
recognize a position and an orientation of another robot in the task database on the basis of communication with support server, and
designate in the plurality of active sensors disposed in the self robot an active sensor which has a possibility to interfere with either of the plurality of active sensors disposed in the other robot on the basis of the determination result and the recognition result, and
the second processing element is configured to evaluate a degree of contribution of each of the plurality of active sensors to a task being executed by the self robot,
store the degree of contribution in the task database on the basis of communication with the support server,
recognize at least the degree of contribution of an active sensor of the other robot designated by the first processing element in the task database on the basis of communication with the support server,
compare the degree of contribution of the designated active sensor of the self robot with the degree of contribution of the designated active sensor of the other robot on the basis of the determination result and the recognition result, and
decrease an output intensity of the designated active sensor of the self robot on a condition that the degree of contribution of the designated active sensor of the self robot is lower than the degree of contribution of the designated active sensor of the other robot.
2. The robot according to claim 1 is provided with a plurality of first active sensors directed to a plurality of directions for determining a position or an orientation of an object or for identifying the object as the active sensors, and
the second processing element evaluates higher the degree of contribution to a task by a first active sensor which contributes to determining the position or the orientation of the object or identifying the object in the plurality of the first active sensors if the task is recognized being executed by the self robot on the basis of a determination result of the position or the orientation of the object or an identification result of the object.
3. The robot according to claim 2, wherein the second processing element controls the actions of the robot to displace the position of the object or to guide the object so as to match the directivity of another first active sensor which is not corresponded to the designated active sensor to the orientation of the object when the output intensity of a first active sensor which is corresponded to the designated active sensor and is outputting signals for determining the position or the orientation of the object or for identifying the object is decreased.
4. The robot according to claim 1 is provided with a second active sensor directed to a detection region for determining a position of an object located in the detection region as the active sensor, and
the second processing element evaluates higher the degree of contribution to a task by the second active sensor if the task is recognized being executed by the self robot on the basis of a determination result on the position of the object located in the detection region.
5. The robot according to claim 1, wherein the second processing element recognizes a priority level of the task being executed by the robot, and evaluates higher the degree of contribution of the active sensor to the task if the priority level is greater.
6. A task execution system composed of a plurality of robots and the support server in claim 1.