WO2009136319A1

WO2009136319A1 - System and method for training motion tasks of a person

Info

Publication number: WO2009136319A1
Application number: PCT/IB2009/051736
Authority: WO
Inventors: Richard D. Willmann; Gerd Lanfermann; Annick A. A. Timmermans; Stefan Winter; Juergen Te Vrugt
Original assignee: Koninklijke Philips Electronics N.V.; Philips Intellectual Property & Standards Gmbh
Priority date: 2008-05-08
Filing date: 2009-04-29
Publication date: 2009-11-12

Abstract

A system for training motion tasks of a person comprises a data processing unit (10), a motion sensor unit (13), a motion sequence database (15), a performance threshold database (16) and a progression rule database (17) in communication with the data processing unit (10). The motion sequence database (15) comprises data representative of motion tasks to be trained. Data is structured into individual tasks, tasks into individual sub- tasks and these into individual exercises. The data processing unit (10) compares the data from the motion sensor (13) with data stored in the motion sequence database (15), calculates a measurement of performance for the exercise, compares the calculation result with predefined thresholds stored in the performance threshold database (16) and decides whether to progress to a subsequent individual exercise according to a rule stored in the progression rule database (17). A scheduling module (18) may allocate exercise times and detect conflicting schedules.

Description

System and method for training motion tasks of a person

BACKGROUND OF THE INVENTION

The present invention relates to a system and a method for training motion tasks of a person. More specifically, it relates to a system for training motion tasks of a person comprising a data processing unit, a motion sensor unit, a motion sequence database, a performance threshold database, and a progression rule database. Furthermore, it relates to a method for training motion tasks of a person, wherein the tasks are structured into individual sub-tasks and the sub-tasks are structured into individual exercises.

Upper limb impairments are among the most common forms of neurological deficits after a stroke and lead to the patient being dependent on help from nurses and carers. Regaining independence has shown to be a key motivating factor in patients. This means for the patients that they need to relearn to perform tasks of everyday life such as drinking from a cup, eating with knife and fork, etc. Modern physiotherapy is therefore directed towards a task-oriented training. However, training a complex task is only possible if the therapist decomposes the complex task into a series of sub-tasks that are trained in a series of progressing difficulty and ultimately lead to training and re-learning the complex task.

Conventional physical therapy is time-consuming and requires the direct physical interaction of the patient and the therapist. This is costly and may not be practical in the case that the therapist needs to travel between patient's homes.

Regarding a remote site medical intervention system, US 5,810,747 discloses an interactive intervention system used for monitoring a patient suffering from neurological disorders of movement or a subject seeking to improve skill performance and assisting their training. A patient (or trainee) station is used in interactive training. The patient (or trainee) station includes a computer. A supervisor station is used by, for example, a medical or other professional. The patient (or trainee) station and the supervisor station can communicate with each other, for example, over the internet or over a local area network. The patient (or trainee) station may be located remotely or locally with respect to the supervisor station. Sensors collect physiological information and physical information from the patient or subject while the patient or subject is undergoing training. This information is provided to the supervisor station. It may be summarized and displayed to the patient/subject and/or the supervisor. The patient/subject and the supervisor can communicate with each other, for example, via video in real time. An expert system and neural network determine a goal to be achieved during training. There may be more than one patient (or trainee) station, thus allowing the supervisor to supervise a number of patients/subjects concurrently. A rehabilitation protocol according to US 5,810,747 consists of a series of

(training) tasks and these tasks, in turn, may consist of a series of sub-tasks which are further decomposed into a series of elements. A task might be the restoration of the ability to drink a glass of water. Learning to reach for, pick up a glass of water, bring it to the mouth and drink from it might include a number of sub-tasks such as restoring the flexion and extension response in various planes (e.g. sagittal and transverse) of both arm, forearm, wrist, and fingers, as well as adductive movements where appropriate. Each task is then segmented into a series of elements such as the sequence of first training inhibition of spastic muscles followed by facilitation of the appropriate agonist or antagonist.

US 5,810,747 is directed towards gathering electromyographic (EMG) data and processing these sensor signals with fuzzy logic methods and neural networks in order to decide whether an element to be performed has been executed successfully. However, these sensors may not be suited for all monitoring tasks. For example, the signals of muscles which are covered by other muscles may be difficult to read unless an electrode is inserted into the muscle. Anatomically complex muscular structures may not be reflected sufficiently by surface EMG readings. Furthermore, no information can be gathered about the range of motion or speed of motion of a muscle or the associated limb.

Despite this effort there still exists a need in the art for an improved home rehabilitation or training system.

SUMMARY OF THE INVENTION

Accordingly, the present invention is directed towards a system for training motion tasks of a person comprising: a data processing unit, a motion sensor unit, a motion sequence database, a performance threshold database, and a progression rule database; wherein the motion sensor unit, the motion sequence database, the performance threshold database and the progression rule database are in communication with the data processing unit; wherein the motion sensor unit is adapted to transmit data representative of the motions of the person to the data processing unit; wherein the motion sequence database comprises data representative of the motion tasks to be trained, the data being structured into individual tasks, the tasks being structured into individual sub-tasks and the sub-tasks being structured into individual exercises; and wherein the data processing unit is adapted to process data from the motion sensor unit representative of the motions of the person during execution of an individual exercise; the processing comprising the comparison of the data from the motion sensor with data stored in the motion sequence database, calculating a measurement of performance for the exercise, comparing the calculation result with pre-defined thresholds stored in the performance threshold database and deciding whether to progress to a subsequent individual exercise according to a rule stored in the progression rule database.

The present invention is further directed towards a method for training motion tasks of a person, wherein the tasks are structured into individual sub-tasks and the sub-tasks are structured into individual exercises, the method comprising the steps of: a) gathering data representative of the motion of the person during the execution of an individual exercise; b) comparing the data with stored data representative of the motion tasks to be trained; c) calculating a measurement of the performance during the execution of an individual exercise; d) comparing the calculation result with pre-defined thresholds; e) deciding whether to progress to a subsequent individual exercise according to a progression rule.

In summary, the present invention allows to conduct unsupervised home rehabilitation training without permanent contact to a therapist which focuses on the actual individual movements to be trained.

BRIEF DESCRIPTION OF THE DRAWINGS

Fig. 1 shows a system according to the present invention Fig. 2 shows a sequence of sub-tasks where one sub-task is structured into individual exercises

Fig. 3a and 3b show a visual scheduling representation in the form of pie charts

Fig. 4 shows a flow diagram for a method according to the present invention DETAILED DESCRIPTION OF THE INVENTION

Before the invention is described in detail it is to be understood that this invention is not limited to the particular component parts of the devices described or process steps of the methods described as such devices and methods may vary. It is also to be understood that the terminology used herein is for purposes of describing particular embodiments only and is not intended to be limiting. It must be noted that as used in the specification and the appended claims the singular forms "a," "an", and "the" include singular and/or plural referents unless the context clearly dictates otherwise. Thus, for example, reference to "a sensor" may include several sensors, and the like. The system according to the present invention is now described with further reference to Fig. 1. A data processing unit 10 is in communication with motion sensor unit 13, motion sequence database 15, performance threshold database 16 and progression rule database 17.

The motion sequence database 15 comprises data representative of the motions to be trained. The motions to be trained are structured and stored in the database as individual tasks. An example for such an individual task may be the drinking from a cup or the picking up of a telephone receiver. In the present invention it is recognized that the individual tasks need to be structured into individual sub-tasks and the individual sub-tasks need to be structured into individual exercises. Thus, the motion sequence database 15 can be seen as a template database for the exercises. These templates may serve to identify the kind of exercise that the person is undertaking. Furthermore, the templates may be used to display the exercise movements to the person, thus instructing him about the correct execution of the movements.

The performance threshold database 16 comprises data representative of thresholds for calculated performances during an exercise that indicate the successful execution. Permissible ranges are assigned to the performance measurements. Thus, for example, a threshold for a range of motion may be stored as angular values in a plane or a cone. A threshold for a mean velocity may be a lower threshold meaning that an exercise is deemed successful if a limb is moved above a certain speed. An upper threshold for a mean velocity may mean that an exercise is deemed successful if a limb is controlled so precisely that the speed does not rise above a certain value. A threshold for the mean jerk of a limb may mean a numerical value for the mean amplitude of the motion of the limb.

The progression rule database 17 comprises rules stating when a pre-defined combination of performance measurements, taken in conjunction with their thresholds, shall deem an exercise to be executed successfully. A rule may formalize the completion of an exercise wherein performance measurements remain within their assigned thresholds. Additional rules may define a transition to the next exercise after the patient has executed a pre-defined number of repetitions of an exercise. This helps to avoid boredom and frustration. In other rules the focus is on the result achieved, such as if the patient was able to actually lift a cup. For this, sensors can also be placed on objects other than the patient's body such as the aforementioned cup. It is also possible that progression rules comprise provisions and conditions for handling manual input by the person. Such an input may be, for example, the pressing of a button to override or terminate an exercise. The motion sequence database 15, the performance threshold database 16, and the progression rule database 17 may be separate physical or logical entities. However, they may also be combined. For example, the data of the performance threshold database 16 can be integrated into the template data of the motion sequence database 15.

The motion sensor unit 13 serves to collect data representative of the motion of the person executing an exercise. For example, the motion of a limb or the motion within a joint may be monitored. The motion sensor unit 13 may be attached directly to the person at appropriate locations. This may be the case when a plurality of inertial sensors is embedded in a garment worn by the person or when the sensors are strapped to the person's limbs. It is also possible that the motion sensor unit 13 comprises a set of optical marks on the person and an optical tracking system to determine the motion of the person. The transmission of data from the motion sensor unit 13 may be undertaken wirelessly or via a wired connection. Examples for wireless connections are the IEEE 802.11 protocols, the bluetooth protocol or transmissions by infrared or visible light.

The data from the motion sensor unit 13 is then handled by the data processing unit 10. In the processing a measurement of the performance during the exercise is calculated. This may be undertaken via performance measurement calculation algorithm 11 within the data processing unit 10. Performance measurements to be calculated include parameters such as the range of motion of a limb or of a joint. The range of motion can be expressed as an angular range. Other performance measurements may be the mean velocity of a limb or the mean jerk of a limb. Having calculated these measurements it is then decided whether the exercise has been performed successfully and therefore the patient may move on to train the next exercise. This may be done by the progression decision algorithm 12 within the data processing unit 10. A specific rule is accessed in the progression rule database 17 and applied onto the calculated performance measurements. The structuring of individual tasks into individual sub-tasks and the structuring of the individual sub-tasks into individual exercises according to the present invention is described with further reference to Fig. 2. By way of example, the task of drinking from a cup is shown. Firstly, this task is sub-divided into sub-tasks 20 to 24. The first sub-task 24 is the reaching out to a cup. This involves the movement of an arm. The second sub-task 21 is the grasping of the cup which involves the hand of the patient. Next comes the lifting of the cup 22, combining the use of arm and hand muscles. This is followed by the bringing of the hand which bears the cup to the mouth 23 and the pouring of the cup contents into the mouth 24. The pouring is effected by a pronation of the hand involving the lower arm muscles. The sub-task of reaching out to a cup 20 is further broken down into the individual exercises 25 to 28. The first exercise is a pendular reaching exercise 25. This is trained until progression rule Rl decides that the training has been a success. The patient then goes on to the second exercise 26 which requires an excentric flexion against gravity. After satisfying progression rule R2 the horizontal reaching exercise 27 is trained. Following progression rule R3 the concentric flexion exercise 28 is next. After conclusion of this exercise and if progression rule R4 is met the patient has concluded the sub-task of reaching out to a cup 20 and can commence training of the exercises of the next sub-task 21.

With additional reference again to Fig. 1, in one embodiment the system according the present invention further comprises a feedback unit 14 adapted to display information and/or to receive commands from an operator. The feedback unit 14 may be in communication with the data processing unit 10. By employing a feedback unit the patient may be informed directly if the exercise has been executed successfully. The feedback may take the form of optical, acoustical or vibrational feedback. It may also be a computer display screen. Furthermore, a physiotherapist may access the feedback unit and review the progress of the patient. It is also possible that the therapist edits parameters such as threshold values to account for the progress of the patient. The feedback unit 14 can also be in communication with the data processing unit 10 via a computer network. Suitable computer networks comprise local area networks, wide area networks and the internet. The feedback unit 14 for displaying information to the patient may be physically located near the patient and the feedback unit 14 for the therapist may be located with the therapist and communicate with the data processing unit 10 via a computer network. This enables a remote supervision of the patients which saves the therapist's time and makes therapy more efficient.

In a further embodiment of the system according to the present invention the motion sensor unit 13 comprises sensors selected from the group comprising acceleration sensors, inertial sensors, gravity sensors and/or optical sensors. Acceleration sensors, inertial sensors and gravity sensors may also be combined into a highly integrated solid state sensor. This has the advantage of using very little space on the patient's body. Optical sensors have the advantage that the system can be integrated into optical motion capture systems to evaluate the movements of the patient. As an addition, electromyographic (EMG) sensors may be used together with the aforementioned sensors. Especially surface EMG sensors can give information on how much a muscle is contracting. In the case of exercises where a part of the body needs to remain static it is therefore possible to distinguish whether a muscle is contracted or relaxed. This may also be used in order to determine the success of an exercise. In a further embodiment of the system according to the present invention the measurement of performance that is calculated comprises the range of motion for the trunk, range of motion for the shoulder, range of motion for the elbow, range of motion for the hip, range of motion for the knee, range of motion for the ankle, range of motion for the head, mean velocity of the head, mean velocity of the hand, mean velocity of the foot, mean jerk of the head, mean jerk of the hand and/or mean jerk of the foot. These measurements can be combined to adequately reflect the exercise to be performed. With respect to the range of motion, this can be expressed as plane or cone angles, depending on the joint addressed. The plane may further be specified as the sagittal plane, the frontal plane, the horizontal plane or combinations of these. In a further embodiment of the system according to the present invention the progression rule database 17 comprises a rule linking the results of the comparisons of at least two calculated measurements of performance with their respective thresholds by operations of Boolean algebra. In its simplest form, a rule may take the form of a logical AND expression. For example, if the range of motion of a first body part does not exceed a threshold AND the range of motion around a first joint does not fall below a threshold AND the range of motion of a second joint lies within upper and lower threshold boundaries then the exercise was successful and the patient may commence the next exercise.

In a further embodiment of the system according to the present invention the motion sequence database 15 further comprises data indicating the time needed for the execution of a sub-task, data classifying sub-tasks into pre-defined categories, default plans for scheduling a sequence of sub-tasks over a period of time and data indicating the maximum time allowed for a person per training session. Additionally, the data processing unit 10 further comprises a scheduling module 18 which is adapted to allocate sub-tasks to be executed at pre-determined times, adapted to detect conflicting schedules and adapted to generate a visual representation of schedules. This embodiment supports a therapist in defining default plans for each task. These default plans can be assigned to a patient resulting in an automatically generated individual schedule which can then be further adapted to fit the patient's needs. The therapist is also supported in resolving conflicts between the schedules resulting from the use of several default plans. This is advantageous as normally the definition of a patient-specific schedule would require the therapist to plan each sub-task separately for each patient although the basic structure of a task-oriented training plan is similar for many patients. In addition, the therapist normally does not receive any guidance in defining a time-efficient but not overexerting training plan for a patient.

A default plan may comprise a clear text name that uniquely identifies the default plan and a description that gives more details about the default plan and the intended patient group. It may further comprise a representation of sessions that contain sub-tasks. The sessions are scheduled at certain times on certain days. A session is defined as the period during which several sub-tasks are executed in sequence without major breaks. In the default plan the days are not associated with a specific date.

An example for a default plan defining a general schedule for a single task is given in the following table 1.

Table 1

Each task may have several default plans that account for differences in patients such as different capability levels.

In order to support the therapist in defining a default plan the database comprises data indicating the time needed for the execution of a sub-task and data classifying sub-tasks into pre-defined categories. In this embodiment, the time needed for the execution of a sub-task may also be further detailed into the time needed for the execution of the individual exercises. Data classifying sub-tasks into pre-defined categories may reflect categories such as how certain sub-tasks are equivalent to each other, how mentally or physically demanding certain sub-tasks are or which functional goal is to be achieved. The required time and classification are part of the description of the sub-task and are entered when the sub-task is defined. When the therapist starts composing a default plan sessions may be visualized on a display screen by empty pie charts. Each sub-task is then represented by a part of a pie chart, wherein its size α corresponds to the ratio of the maximum time allowed per session ts and the time required by the sub-task tt according to the equation

α = 360° x (tt/ts)

The maximum time allowed per session is defined by the maximum time that is good for the patient according to his mental capacity and attention span. It should prevent overuse of the system by the patient and deeds to be entered by the therapist based on the patient's condition and good clinical practice in rehabilitation. Typically, it would be around 20 minutes. Sub-tasks that belong into the same category may be marked by visual means such as coloring or hatching. The pie chart fills up when the therapist adds sub-tasks. This may be done via drag-and-drop operations on a computer. As the remaining time of the session decreases those sub-tasks that do not fit anymore due to time constraints are disabled so that they cannot be added to the session anymore by the therapist.

Fig. 3a and 3b show such pie charts. In Fig. 3a, empty circle 30 represents an empty schedule. Pie segments 31 to 36 represent different sub-tasks with different lengths. By way of hatching, similarities are expressed within the sub-tasks. Pie segments 31 and 32 are similar, segments 33, 34 and 35 are similar and segment 36 belongs to another category. Via drag-and-drop operations the therapist can place pie segments into circle 30. The result is shown in Fig. 3b. Two sub-tasks 31, three sub-tasks 33 and three sub-tasks 35 have been entered into the schedule. The remaining time slot 37 is not big enough to accomodate sub- task 36. A scheduling system would therefore disable segment 36 for drag-and-drop operations. In preparation of the scheduling, the therapist and the patient initially agree on rehabilitation tasks such as relearning how to drink from a cup or eating with knife and fork. In an initial assessment the therapist determines the present capabilities of the patient. For each chosen task the therapist then chooses a default plan and an entry point according to the patient's capabilities. This way the patient does not have to start with the first day if he has no need to train the sub-tasks contained in that day. The therapist also chooses a start date (offset) when the patient is supposed to start his training. Based on the offset and the default plan the sub-tasks of the corresponding task are automatically entered into the patient's individual schedule by assigning each day a specific date. As an option certain dates such as weekends can be omitted.

An example for such an individual schedule based on a default plan and an offset is given in the following table 2.

Table 2

The therapist may further individualize the patient's schedule, for example by inserting additional days of rest, planning additional sessions or by moving sub-tasks. If the time required for executing all sub-tasks scheduled due to the selection of several default plans exceeds the time allowed in a certain session (ts) or sub-tasks from different default plans within a specific session belong to the same category the scheduling algorithm generates a warning and focuses the therapist's attention on these conflicts. By selecting the conflicting session the therapist is offered the pie chart with the sub-tasks from all involved default plans. Then the therapist can resolve the conflict, for example by removing sub-tasks that possibly belong to the same category or by reducing the number of repetitions for certain sub-tasks.

The following tables show a superposition of a first default plan (3a) and a second default plan (3b) resulting in the combined plan (3c). In the afternoon session of March 3, 2009 a conflict is detected and the therapist is alerted.

Table 3 a

Table 3b

26.2.2009 27.2.2009 2.3.2009 3.3.2009 4.3.2009

Morning Sub-task 1 Sub-task 9 Sub-task 2 Sub-task 12 Sub-task 6 session Sub-task 2 Sub-task Sub-task 3 Sub-task 13 Sub-task 7

10 Sub-task 14

AfterSub-task 8 Sub-task Sub-task 1 Sub-task 4 Sub-task 5 Sub-task noon Sub-task 9 11 Sub-task 3 Sub-task 8 Sub-task 6 13 session Sub-task Sub-task 7 Sub-task

10 14

Table 3c (combination of table 3a and 3b) with conflict on afternoon of 3.3.2009

In addition to not allowing the addition of further exercises when the remaining time is not sufficient or the manual resolution of conflicts that have been automatically spotted an algorithm might be applied to automatically solve the issues or propose alternative resolutions. The method according to the present invention is now described in connection with the flow chart depicted in Fig. 4. The first step 40 is to display an exercise goal to the patient in order to inform him about the individual exercise that is about to be undertaken. This may be by an acoustic message such as a recorded voice message by a display on a computer screen or the like. During the execution of the exercise motion sensor data is gathered in step 41. The data is representative of the motion of the person during the exercise. In processing the data it is compared with stored representative data of the motion tasks to be trained in step 42 and a performance measurement is calculated in step 43. The application of a progression rule involves a comparison of the calculated performance measurement with pre-defined thresholds in step 44 and the decision whether to progress to a subsequent individual exercise in step 45. Here the flow chart branches. If it is decided that the criteria for a successful execution have not yet been met this is communicated to the patient in step 46 and, by reverting to step 41, the same exercise is repeated. On the other hand if the exercise goal has been met this is communicated to the patient in step 47 and a new exercise commences in step 40.

It is also within the scope of the invention that besides the decision to repeat the current exercise and to progress to the next exercise an option to quit the execution of exercises is provided. In the flow chart of Fig. 4, this option may be installed between step 45 and 46 and 45 and 47 respectively. The reason to quit could be that the patient repeats the exercises more often that would be beneficial for him or that the patient has spent too much time in one exercise already.

In an embodiment of the method according to the present invention, the gathering of data in step a) is undertaken using sensors selected from the group comprising acceleration sensors, inertial sensors, gravity sensors and/or optical sensors. In a further embodiment of the method according to the present invention the progression rule in step e) links the results of the comparisons of at least two calculated measurements of performance with their respective thresholds by operations of Boolean algebra. This has already been described in connection with the system according to the invention. In a further embodiment of the method according to the present invention furthermore a scheduling module allocates sub-tasks to be executed at pre-determined times detects conflicting schedules and generates a visual representation of schedules. This has already been described in connection with the system according to the invention. In order to give an example, the pendular reaching exercise 25 as shown in Fig. 2 is described in more detail with reference to the method according to the present invention. The limb motions are recorded by body- worn inertial sensors on the trunk, shoulder, upper arm, and lower arm. These sensors and sensor positions allow the reconstruction of the body posture and joint angles as well as the computation of the range of motion of the relevant body parts.

After each repetition of the exercise performance measurements are calculated for this repetition. In the case of the pendular reaching exercise the performance measurements may comprise the ranges of motion of the trunk Rt of the shoulder in the sagittal plane Rs and of the elbow in the sagittal plane Re, furthermore the mean velocity of the hand V and the mean jerk of the hand J.

These performance measurements are then compared to threshold measurements which define permissible values or ranges for the measurements. For example, the threshold value Tt for the range of motion for the trunk may be an angle of 5 degrees. This means that the trunk should not sway by more than 5 degrees during the exercise.

Likewise, a threshold value Ts for the range of motion for the shoulder in the sagittal plane, a threshold range Tel ... Te2 for the range of motion for the elbow in the sagittal plane, a threshold value Tv for the mean velocity of the hand and a threshold value Tj for the mean jerk of the hand may be established. The progression rule Rl in Fig. 2 then determines whether the exercise has been executed satisfactorily. In this case the trunk should remain sufficiently steady while a sufficiently smooth and speedy movement of the upper and lower arm is performed in the sagittal plane. The rule may take the following boolean form:

(Rt < Tt) AND (Rs > Ts) AND (Tel < Re < Te2) AND (V > Tv) AND (J < Tj)

If the boolean value for the progression rule is TRUE then the patient can practice the next exercise. Otherwise a repetition of the current exercise will be recommended. In this the patient may receive feedback on the shortcomings and is encouraged to keep on practising within the exercise and sub-task.

The present invention is also directed towards the use of a system according to the invention for training motion tasks of a person. Furthermore, it also encompasses a storage medium, comprising computer-readable instructions enabling a computer to carry out the method according to the invention. Such instructions may comprise executable code segments reflecting the steps a) to e) of the method. Additionally, the present invention also envisions a computer program product for enabling a computer to carry out the method of the invention.

To provide a comprehensive disclosure without unduly lengthening the specification the applicant hereby incorporates by reference each of the patents and patent applications referenced above.

The particular combinations of elements and features in the above detailed embodiments are exemplary only; the interchanging and substitution of these teachings with other teachings in this and the patents/applications incorporated by reference are also expressly contemplated. As those skilled in the art will recognize, variations, modifications, and other implementations of what is described herein can occur to those of ordinary skill in the art without departing from the spirit and the scope of the invention as claimed. The foregoing specification has illustrated the present invention with respect to the rehabilitation of a stroke patient. However, the invention is by no means restricted to this. Other rehabilitation schedules are also contemplated. Additionally, the present invention may be used in the training of healthy persons wishing to learn a complex movement. An example for this is a golfer who would like to improve his golf swing.

Accordingly, the foregoing description is by way of example only and is not intended as limiting. The invention's scope is defined in the following claims and the equivalents thereto. Furthermore, reference signs used in the description and claims do not limit the scope of the invention as claimed.

Claims

CLAIMS:

1. A system for training motion tasks of a person comprising: a data processing unit (10), a motion sensor unit (13), a motion sequence database (15), a performance threshold database (16) and a progression rule database (17); wherein the motion sensor unit (13), the motion sequence database (15), the performance threshold database (16) and the progression rule database (17) are in communication with the data processing unit (10); wherein the motion sensor unit (13) is adapted to transmit data representative of the motions of the person to the data processing unit; wherein the motion sequence database (15) comprises data representative of the motion tasks to be trained, the data being structured into individual tasks, the tasks being structured into individual sub-tasks and the sub-tasks being structured into individual exercises; and wherein the data processing unit (10) is adapted to process data from the motion sensor unit

(13) representative of the motions of the person during execution of an individual exercise; the processing comprising the comparison of the data from the motion sensor (13) with data stored in the motion sequence database (15), calculating a measurement of performance for the exercise, comparing the calculation result with pre-defined thresholds stored in the performance threshold database (16) and deciding whether to progress to a subsequent individual exercise according to a rule stored in the progression rule database (17).

2. System according to claim 1, further comprising a feedback unit (14) adapted to display information and/or to receive commands from an operator.

3. System according to claim 2, wherein the feedback unit (14) is in communication with the data processing unit (10) via a computer network.

4. System according to claim 1, wherein the motion sensor unit (13) comprises sensors selected from the group comprising acceleration sensors, inertial sensors, gravity sensors and/or optical sensors.

5. System according to claim 1, wherein the measurement of performance that is calculated comprises the range of motion for the trunk, range of motion for the shoulder, range of motion for the elbow, range of motion for the hip, range of motion for the knee, range of motion for the ankle, range of motion for the head, mean velocity of the head, mean velocity of the hand, mean velocity of the foot, mean jerk of the head, mean jerk of the hand and/or mean jerk of the foot.

6. System according to claim 1, wherein the progression rule database (17) comprises a rule linking the results of the comparisons of at least two calculated measurements of performance with their respective thresholds by operations of Boolean algebra.

7. System according to claim 1, wherein the motion sequence database (15) further comprises data indicating the time needed for the execution of a sub-task, data classifying sub-tasks into pre-defined categories, default plans for scheduling a sequence of sub-tasks over a period of time, data indicating the maximum time allowed for a person per training session, and wherein the data processing unit (10) further comprises a scheduling module (18) which is adapted to allocate sub-tasks to be executed at pre-determined times, adapted to detect conflicting schedules and adapted to generate a visual representation of schedules.

8. Method for training motion tasks of a person, wherein the tasks are structured into individual sub-tasks and the sub-tasks are structured into individual exercises, the method comprising the steps of: a) gathering data representative of the motion of the person during the execution of an individual exercise; b) comparing the data with stored data representative of the motion tasks to be trained; c) calculating a measurement of the performance during the execution of an individual exercise; d) comparing the calculation result with pre-defined thresholds; e) deciding whether to progress to a subsequent individual exercise according to a progression rule.

9. Method according to claim 8, wherein the gathering of data in step a) is undertaken using sensors selected from the group comprising acceleration sensors, inertial sensors, gravity sensors and/or optical sensors.

10. Method according to claim 8, wherein the progression rule in step e) links the results of the comparisons of at least two calculated measurements of performance with their respective thresholds by operations of Boolean algebra.

11. Method according to claim 8, wherein furthermore a scheduling module allocates sub-tasks to be executed at pre-determined times, detects conflicting schedules and generates a visual representation of schedules.

12. Use of a system according to claim 1 for training motion tasks of a person.

13. Storage medium, comprising computer-readable instructions enabling a computer to carry out the method of claim 8.

14. Computer program product for enabling a computer to carry out the method of claim 8.