Patents by Inventor George KONIDARIS
George KONIDARIS has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 11970161Abstract: A motion planner of an autonomous vehicle's computer system uses reconfigurable collision detection architecture hardware to perform a collision assessment on a planning graph for the vehicle prior to execution of a motion plan. For edges on the planning graph, which represent transitions in states of the vehicle, the system sets a probability of collision with a dynamic object in the environment based at least in part on the collision assessment. Depending on whether the goal of the vehicle is to avoid or collide with a particular dynamic object in the environment, the system then performs an optimization to identify a path in the resulting planning graph with either a relatively high or relatively low potential of a collision with the particular dynamic object. The system then causes the actuator system of the vehicle to implement a motion plan with the applicable identified path based at least in part on the optimization.Type: GrantFiled: February 28, 2022Date of Patent: April 30, 2024Assignees: DUKE UNIVERSITY, BROWN UNIVERSITYInventors: Daniel Sorin, William Floyd-Jones, Sean Murray, George Konidaris, William Walker
-
Patent number: 11964393Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change. Various aspects of such robot motion planning are implemented in particular systems and methods that facilitate motion planning of the robot for various environments and tasks.Type: GrantFiled: July 12, 2023Date of Patent: April 23, 2024Assignee: REALTIME ROBOTICS, INC.Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones, Peter Howard, Xianchao Long
-
Publication number: 20230356400Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change.Type: ApplicationFiled: July 17, 2023Publication date: November 9, 2023Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones
-
Publication number: 20230347520Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change. Various aspects of such robot motion planning are implemented in particular systems and methods that facilitate motion planning of the robot for various environments and tasks.Type: ApplicationFiled: July 12, 2023Publication date: November 2, 2023Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones, Peter Howard, Xianchao Long
-
Publication number: 20230347519Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change. Various aspects of such robot motion planning are implemented in particular systems and methods that facilitate motion planning of the robot for various environments and tasks.Type: ApplicationFiled: July 12, 2023Publication date: November 2, 2023Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones, Peter Howard, Xianchao Long
-
Patent number: 11745346Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change.Type: GrantFiled: November 22, 2021Date of Patent: September 5, 2023Assignee: REALTIME ROBOTICS, INC.Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones
-
Patent number: 11738457Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change. Various aspects of such robot motion planning are implemented in particular systems and methods that facilitate motion planning of the robot for various environments and tasks.Type: GrantFiled: March 19, 2019Date of Patent: August 29, 2023Assignee: REALTIME ROBOTICS, INC.Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones, Peter Howard, Xianchao Long
-
Patent number: 11634126Abstract: A motion planner performs motion planning with collision assessment, using a motion planning lattice that represents configuration states of a primary agent (e.g., autonomous vehicle) as nodes and transitions between states as edges. The system may assign cost values to edges, the cost values representing probability or likelihood of collision for the corresponding transition. The cost values may additionally or alternatively represent a severity of collision, for example generated via a parametric function with two or more parameters and one or more weights. A primary agent and/or dynamic obstacles may be represented as respective oriented bounding boxes. Some obstacles (e.g., road markings, edge of road) may be represented as curves.Type: GrantFiled: May 26, 2020Date of Patent: April 25, 2023Assignee: REALTIME ROBOTICS, INC.Inventors: William Floyd-Jones, Bryce Willey, George Konidaris, Xianchao Long
-
Publication number: 20220176951Abstract: A motion planner of an autonomous vehicle's computer system uses reconfigurable collision detection architecture hardware to perform a collision assessment on a planning graph for the vehicle prior to execution of a motion plan. For edges on the planning graph, which represent transitions in states of the vehicle, the system sets a probability of collision with a dynamic object in the environment based at least in part on the collision assessment. Depending on whether the goal of the vehicle is to avoid or collide with a particular dynamic object in the environment, the system then performs an optimization to identify a path in the resulting planning graph with either a relatively high or relatively low potential of a collision with the particular dynamic object. The system then causes the actuator system of the vehicle to implement a motion plan with the applicable identified path based at least in part on the optimization.Type: ApplicationFiled: February 28, 2022Publication date: June 9, 2022Inventors: Daniel SORIN, William FLOYD-JONES, Sean MURRAY, George KONIDARIS, William WALKER
-
Patent number: 11292456Abstract: A motion planner of an autonomous vehicle's computer system uses reconfigurable collision detection architecture hardware to perform a collision assessment on a planning graph for the vehicle prior to execution of a motion plan. For edges on the planning graph, which represent transitions in states of the vehicle, the system sets a probability of collision with a dynamic object in the environment based at least in part on the collision assessment. Depending on whether the goal of the vehicle is to avoid or collide with a particular dynamic object in the environment, the system then performs an optimization to identify a path in the resulting planning graph with either a relatively high or relatively low potential of a collision with the particular dynamic object. The system then causes the actuator system of the vehicle to implement a motion plan with the applicable identified path based at least in part on the optimization.Type: GrantFiled: January 4, 2019Date of Patent: April 5, 2022Assignees: DUKE UNIVERSITY, BROWN UNIVERSITYInventors: Daniel Sorin, William Floyd-Jones, Sean Murray, George Konidaris, William Walker
-
Publication number: 20220080594Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change.Type: ApplicationFiled: November 22, 2021Publication date: March 17, 2022Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones
-
APPARATUS, METHOD AND ARTICLE TO FACILITATE MOTION PLANNING IN AN ENVIRONMENT HAVING DYNAMIC OBJECTS
Publication number: 20220057803Abstract: A motion planner of a computer system of a primary agent, e.g., an autonomous vehicle, uses reconfigurable collision detection architecture hardware to perform a collision assessment on a planning graph for the primary agent prior to execution of a motion plan. For edges on the planning graph, which represent transitions in states of the primary agent, the system sets a probability of collision with another agent, e.g., a dynamic object, in the environment based at least in part on the collision assessment. Depending on whether the goal of the primary agent is to avoid or collide with a particular dynamic object in the environment, the system then performs an optimization to identify a path in the resulting planning graph with either a relatively low or relatively high potential of a collision with the particular dynamic object. The system then causes the actuator system of the primary agent to implement a motion plan with the applicable identified path based at least in part on the optimization.Type: ApplicationFiled: December 4, 2019Publication date: February 24, 2022Inventors: Daniel SORIN, William FLOYD-JONES, Sean MURRAY, George KONIDARIS, William WALKER -
Patent number: 11235465Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change.Type: GrantFiled: February 5, 2019Date of Patent: February 1, 2022Assignee: REALTIME ROBOTICS, INC.Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones
-
Publication number: 20210023706Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change. Various aspects of such robot motion planning are implemented in particular systems and methods that facilitate motion planning of the robot for various environments and tasks.Type: ApplicationFiled: March 19, 2019Publication date: January 28, 2021Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones, Peter Howard, Xianchao Long
-
Publication number: 20200377085Abstract: A motion planner performs motion planning with collision assessment, using a motion planning lattice that represents configuration states of a primary agent (e.g., autonomous vehicle) as nodes and transitions between states as edges. The system may assign cost values to edges, the cost values representing probability or likelihood of collision for the corresponding transition. The cost values may additionally or alternatively represent a severity of collision, for example generated via a parametric function with two or more parameters and one or more weights. A primary agent and/or dynamic obstacles may be represented as respective oriented bounding boxes. Some obstacles (e.g., road markings, edge of road) may be represented as curves.Type: ApplicationFiled: May 26, 2020Publication date: December 3, 2020Inventors: William Floyd-Jones, Bryce Willey, George Konidaris, Xianchao Long
-
Publication number: 20190240835Abstract: A robot control system determines which of a number of discretizations to use to generate discretized representations of robot swept volumes and to generate discretized representations of the environment in which the robot will operate. Obstacle voxels (or boxes) representing the environment and obstacles therein are streamed into the processor and stored in on-chip environment memory. At runtime, the robot control system may dynamically switch between multiple motion planning graphs stored in off-chip or on-chip memory. The dynamically switching between multiple motion planning graphs at runtime enables the robot to perform motion planning at a relatively low cost as characteristics of the robot itself change.Type: ApplicationFiled: February 5, 2019Publication date: August 8, 2019Inventors: Daniel Sorin, George Konidaris, Sean Murray, William Floyd-Jones
-
Publication number: 20190217857Abstract: A motion planner of an autonomous vehicle's computer system uses reconfigurable collision detection architecture hardware to perform a collision assessment on a planning graph for the vehicle prior to execution of a motion plan. For edges on the planning graph, which represent transitions in states of the vehicle, the system sets a probability of collision with a dynamic object in the environment based at least in part on the collision assessment. Depending on whether the goal of the vehicle is to avoid or collide with a particular dynamic object in the environment, the system then performs an optimization to identify a path in the resulting planning graph with either a relatively high or relatively low potential of a collision with the particular dynamic object. The system then causes the actuator system of the vehicle to implement a motion plan with the applicable identified path based at least in part on the optimization.Type: ApplicationFiled: January 4, 2019Publication date: July 18, 2019Inventors: Daniel SORIN, William FLOYD-JONES, Sean MURRAY, George KONIDARIS, William WALKER