Fusion of sensor and map data using constraint based optimization
First Claim
1. A computer-implemented method of simultaneously tracking a tracked device and determining a location of features, comprising:
- obtaining a sensor data from the tracked device, the sensor data including a location data and a dead reckoning sensor data;
determining a dead reckoning path data based on the sensor data;
detecting one or more features based on the sensor data;
detecting a location for each feature based on the dead reckoning path data;
determining at least one constraint based on the sensor data; and
optimizing the dead reckoning path data and updating the location of each feature using a convex simultaneous location and mapping algorithm comprising;
defining a convex objective function for the dead reckoning path data;
minimizing the convex objective function based on the at least one constraint;
applying the convex objective function to update the dead reckoning path data; and
updating the location of each feature based on the updated dead reckoning path data.
1 Assignment
0 Petitions
Accused Products
Abstract
Disclosed herein are methods and systems for fusion of sensor and map data using constraint based optimization. In an embodiment, a computer-implemented method may include obtaining tracking data for a tracked subject, the tracking data including data from a dead reckoning sensor; obtaining constraint data for the tracked subject; and using a convex optimization method based on the tracking data and the constraint data to obtain a navigation solution. The navigation solution may be a path and the method may further include propagating the constraint data by a motion model to produce error bounds that continue to constrain the path over time. The propagation of the constraint data may be limited by other sensor data and/or map structural data.
80 Citations
31 Claims
-
1. A computer-implemented method of simultaneously tracking a tracked device and determining a location of features, comprising:
-
obtaining a sensor data from the tracked device, the sensor data including a location data and a dead reckoning sensor data; determining a dead reckoning path data based on the sensor data; detecting one or more features based on the sensor data; detecting a location for each feature based on the dead reckoning path data; determining at least one constraint based on the sensor data; and optimizing the dead reckoning path data and updating the location of each feature using a convex simultaneous location and mapping algorithm comprising; defining a convex objective function for the dead reckoning path data; minimizing the convex objective function based on the at least one constraint; applying the convex objective function to update the dead reckoning path data; and updating the location of each feature based on the updated dead reckoning path data. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A computer readable storage medium comprising instructions that, when executed on a computing system to simultaneously track a tracked device and determine a location of features, cause the computing system to at least:
-
obtain a sensor data from the tracked device, the sensor data comprising a location data and a dead reckoning sensor data; determine a dead reckoning path data based on the sensor data; detect one or more features based on the sensor data detect a location for each feature based on the dead reckoning path data; determine at least one constraint based on the sensor data; and optimize the dead reckoning path data and update the location of each feature using a convex simultaneous location and mapping algorithm comprising instructions that further cause the computing system to at least; define a convex objective function for the dead reckoning path data; minimize the convex objective function based on the at least one constraint; apply the convex objective function to update the dead reckoning path data; and update the location of each feature based on the updated dead reckoning path data. - View Dependent Claims (14, 15, 16, 17, 18, 19, 20, 21, 22, 23)
-
-
24. A computing system for simultaneously tracking a tracked device and determining a location of features comprising:
-
a processor; a memory communicatively coupled to the processor, the memory bearing instructions that, when executed on the processor, cause the computing system to at least; obtain a sensor data from the tracked device, the sensor data comprising a location data and a dead reckoning sensor data; determine a dead reckoning path data based on the sensor data; detect one or more features based on the sensor data; detect a location for each feature based on the dead reckoning path data; determine at least one constraint based on the sensor data; and optimize the dead reckoning path data and update the location of each feature using a convex simultaneous location and mapping algorithm comprising instructions that further cause the computing system to; define a convex objective function for the dead reckoning path data; minimize the convex objective function based on the at least one constraint; apply the convex objective function to update the dead reckoning path data; and update the location of each feature based on the updated dead reckoning path data. - View Dependent Claims (25, 26, 27, 28, 29, 30, 31)
-
Specification