System and method for predicting human posture using a rules-based sequential approach

• US 9,129,077 B2
• Filed: 09/03/2004
• Issued: 09/08/2015
• Est. Priority Date: 09/03/2004
• Status: Expired due to Fees

• Current Assignee: Siemens Product Lifecycle Management Software Incorporated (Siemens AG)
• Original Assignee: Siemens Product Lifecycle Management Software Incorporated (Siemens AG)
• Inventors: Raschke, Ulrich
• Primary Examiner(s): Saxena, Akash
• Application Number:
  US10/933,699
• Publication Number:
  US 20060053108A1
• Time in Patent Office: 4,022 Days
• Field of Search: 345/473
• US Class Current: 1/1
• CPC Class Codes: G06F 2111/04 Constraint-based CAD
• CPC Class Codes: G06F 30/20 Design optimisation, verification or simulation optimisation, verification or simulation of circuit designs G06F30/30

Abstract

According to one embodiment of the invention, a computerized method for predicting posture of a living object includes storing a plurality of posturing rules for a respective activity in a storage location, receiving a start posture of a first living object for the activity, receiving a location of a target for the activity, dividing the activity into a plurality of movements based on the start posture and the location of the target, and determining an end posture of the first living object for the activity. Determining the end posture includes applying at least one of the posturing rules for each of the movements and checking at least one of a plurality of constraints associated with each of the movements.

Claims

1. A computerized method for predicting posture of a physical object, comprising:

storing a plurality of posturing rules for a respective activity in a storage location;

receiving a start posture of a physical object for the activity;

receiving a location of a target for the activity;

dividing the activity into a plurality of movements based on the start posture and the location of the target; and

determining, without using motion capture data, an end posture of the physical object for the activity, comprising;

positioning the physical object using an action specified by at least one of the posturing rules for each of the movements;

checking a resulting state of the physical object against at least one of a plurality of constraints associated with each of the movements; and

adjusting an intermediate posture of the physical object based on a result of the checking step.

2. The computerized method of claim 1, further comprising selecting one of a plurality of modules for the respective activity.

3. The computerized method of claim 1, wherein the plurality of posturing rules comprises:

horizontally positioning the physical object relative to the target;

flexing a torso of the physical object;

rotating a pelvis of the physical object around a vertical axis;

vertically positioning the pelvis of the physical object; and

posturing legs of the physical object.

4. The computerized method of claim 3, wherein the plurality of movements further comprises posturing a head of the physical object.

5. The computerized method of claim 1, wherein the plurality of constraints are selected from the group consisting of:

a balance for the physical object;

a location of a barrier;

a sight line for the physical object;

reachability of the target;

physiological correctness; and

a strength of the physical object.

6. The computerized method of claim 1, wherein the physical object is a human.

7. Logic encoded in media for predicting posture of a physical object, the logic operable to perform the following steps:

store a plurality of posturing rules for a respective activity in a storage location;

receive a start posture of a physical object for the activity;

receive a location of a target for the activity;

divide the activity into a plurality of movements based on the start posture and the location of the target; and

determine, without using motion capture data, an end posture of the physical object for the activity by;

positioning the physical object using an action specified by at least one of the posturing rules for each of the movements,

checking a resulting state of the physical object against at least one of a plurality of constraints associated with each of the movements; and

wherein the logic is further operable to adjust an intermediate posture of the physical object based on a result of the checking step.

8. The logic encoded in media of claim 7, the logic further operable to select one of a plurality of modules for the respective activity.

9. The logic encoded in media of claim 7, wherein the plurality of posturing rules comprises:

horizontally positioning the physical object relative to the target;

flexing a torso of the physical object;

rotating a pelvis of the physical object around a vertical axis;

vertically positioning the pelvis of the physical object; and

posturing legs of the physical object.

10. The logic encoded in media of claim 9, wherein the plurality of movements further comprises posturing a head of the physical object.

11. The logic encoded in media of claim 7, wherein the plurality of constraints are selected from the group consisting of:

a balance for the physical object;

a location of a barrier;

a sight line for the physical object;

reachability of the target;

physiological correctness; and

a strength of the physical object.

12. The logic encoded in media of claim 7, wherein the physical object is a human.

13. A computerized method for predicting posture of a physical object, comprising:

selecting one of a plurality of modules for a respective activity;

storing a plurality of posturing rules for the respective activity in a storage location, the plurality of posturing rules comprising;

horizontally positioning the physical object relative to the target;

flexing a torso of the physical object;

rotating a pelvis of the physical object around a vertical axis;

vertically positioning the pelvis of the physical object; and

posturing legs of the physical object;

receiving a start posture of a physical object for the activity;

receiving a location of a target for the activity;

determining, without using motion capture data, an end posture of the physical object for the activity by;

positioning the physical object using an action specified by at least one of the posturing rules for each of the movements;

checking a resulting state of the physical object against at least one of a plurality of constraints associated with each of the movements; and

adjusting an intermediate posture of the physical object based on a result of the checking step.

14. The computerized method of claim 13, wherein the plurality of constraints are selected from the group consisting of:

a balance for the physical object;

a location of a barrier;

a sight line for the physical object;

reachability of the target;

physiological correctness; and

a strength of the physical object.

15. The computerized method of claim 13, wherein the plurality of movements further comprises posturing a head of the physical object.

16. The computerized method of claim 13, wherein the physical object is a human.