Toro: tracking and observing robot
AssigneeHonda Motor Co., Ltd.
InventorsRakesh Gupta, Deepak Ramachandran
Life of this patent
Estimating the term…
Abstract
The present invention provides a method for tracking entities, such as people, in an environment over long time periods. A region-based model is generated to model beliefs about entity locations. Each region corresponds to a discrete area representing a location where an entity is likely to be found. Each region includes one or more positions which more precisely specify the location of an entity within the region so that the region defines a probability distribution of the entity residing at different positions within the region. A region-based particle filtering method is applied to entities within the regions so that the probability distribution of each region is updated to indicate the likelihood of the entity residing in a particular region as the entity moves.
Claims16
A system for tracking one or more entities comprising:
- an image capture device for capturing image data describing an entity;
- a region generation module for generating a plurality of discrete regions, each region including one or more positions and describing a probability distribution over all positions in a region for one or more entities of interest;
- and
- an observation module coupled to the image capture device and the region generation module configured to, for each region:
- generate a set of particles for the region, each particle associated with an entity within the region;
- determine a weight associated with each particle, the weight describing a likelihood of observing the entity associated with the particle in the region;
- and
- modify the probability distribution associated with the region responsive to the weight associated with each generated particle.
A method for tracking an entity through an environment, the method comprising the steps of:
- generating a plurality of regions, each region including one or more positions and representing a location for the entity, wherein each region is associated with a probability distribution that the entity is located at a position from the one or more positions;
- responsive to receiving data from an image capture device, generating a set of particles for each region, each particle associated with an entity within the region and the set of particles collectively representing a belief about the entity being included in a region;
- determining a weight associated with each particle, the weight describing a likelihood of observing the entity associated with the particle in the region;
- and
- modifying the probability distribution associated with each region responsive to the weight associated with each generated particle.
A computer program product, comprising a computer readable storage medium storing computer instructions for tracking an entity through an environment, the computer instructions, when executed, performing the steps of:
- generating a plurality of regions, each region including one or more positions and representing a location for the entity, wherein each region is associated with a probability distribution that the entity is located at a position from the one or more positions;
- responsive to receiving data from an image capture device, generating a set of particles for each region, each particle associated with an entity within the region and the set of particles collectively representing a belief about the entity being included in a region;
- determining a weight associated with each particle, the weight describing a likelihood of observing the entity associated with the particle in the region;
- and
- modifying the probability distribution associated with each region responsive to the weight associated with each generated particle.
Dependencies are inferred from the claim text.