Patent
Motion planning and task execution using potential occupancy envelopes
العنوان: | Motion planning and task execution using potential occupancy envelopes |
---|---|
Patent Number: | 11919,173 |
تاريخ النشر: | March 05, 2024 |
Appl. No: | 17/400242 |
Application Filed: | August 12, 2021 |
مستخلص: | Spatial regions potentially occupied by a robot (or other machinery) or portion thereof and a human operator during performance of all or a defined portion of a task or an application are computationally estimated. These “potential occupancy envelopes” (POEs) may be based on the states (e.g., the current and expected positions, velocities, accelerations, geometry and/or kinematics) of the robot and the human operator. Once the POEs of human operators in the workspace are established, they can be used to guide or revise motion planning for task execution. |
Inventors: | Denenberg, Scott (Newton, MA, US); Vu, Clara (Cambridge, MA, US); Sobalvarro, Patrick (Harvard, MA, US); Moel, Alberto (Cambridge, MA, US) |
Assignees: | Veo Robotics, Inc. (Waltham, MA, US) |
Claim: | 1. A safety system for enforcing safe operation of machinery performing an activity in a three-dimensional (3D) workspace, the system comprising: a computer memory for storing a model of the machinery and its permitted movements and a task specification; and a processor configured to: computationally generate a 3D spatial representation of the workspace; identify a computational representation of a 3D region of the workspace corresponding to (i) space occupied or potentially occupied by a human within the workspace augmented by a 3D envelope around the human corresponding to anticipated movements of the human within the workspace during performance of the specified task and (ii) a protective separation distance; update the computational representation at intervals no greater than a worst-case time required to bring the machinery to a safe state or a stopping time of the machinery in a direction toward the 3D envelope around the human; computationally generate a motion plan comprising a plurality of different trajectories of the machinery to perform the task; assign a cost value to each of the trajectories based at least in part on relative likelihood among trajectories that human movement within the workspace will alter the 3D region during execution of the trajectory; select one of the trajectories based at least in part on the cost values assigned to the trajectories; and cause the machinery to execute the selected trajectory and perform the specified task without entering the 3D region and/or violating the protective separation distance. |
Claim: | 2. The system of claim 1 , wherein the constrained motion plan implements a safety protocol specifying speed restrictions of the machinery in proximity to a human and a minimum separation distance between the machinery and a human. |
Claim: | 3. The system of claim 1 , wherein the processor is further configured to assign the corresponding cost value to each of the trajectories based at least in part on a length of the trajectory and/or an operation time of the machinery on the trajectory. |
Claim: | 4. The system of claim 1 , further comprising a plurality of sensors distributed about the workspace, each of the sensors being configured to record images of a portion of the workspace within a sensor field of view, the workspace portions collectively covering the entire workspace, wherein the processor is configured to compute the 3D region of the workspace based on images generated by the sensors during performance of the task by the machinery. |
Claim: | 5. The system of claim 4 , wherein the processor is responsive to real-time monitoring of the workspace and is further configured to alter the motion plan in response to a change in the 3D region. |
Claim: | 6. The system of claim 4 , wherein the processor is responsive to real-time monitoring of the workspace and is further configured to recompute the motion plan in response to a change in the 3D region. |
Claim: | 7. A method of enforcing safe operation of machinery performing an activity in a three-dimensional (3D) workspace, the method comprising the steps of: computationally generating a 3D spatial representation of the workspace; identifying a computational representation of a 3D region of the workspace corresponding to (i) space occupied or potentially occupied by a human within the workspace augmented by a 3D envelope around the human corresponding to anticipated movements of the human within the workspace during performance of the specified task and (ii) a protective separation distance; updating the computational representation at intervals no greater than a worst-case time required to bring the machinery to a safe state or a stopping time of the machinery in a direction toward the 3D envelope around the human; computationally generating a motion plan comprising a plurality of different trajectories of the machinery to perform the task; assigning a cost value to each of the trajectories based at least in part on relative likelihood among trajectories that human movement within the workspace will alter the 3D region during execution of the trajectory; selecting one of the trajectories based at least in part on the cost values assigned to the trajectories; and causing the machinery to execute the selected trajectory and perform the specified task without entering the 3D region and/or violating the protective separation distance. |
Claim: | 8. The method of claim 7 , wherein the constrained motion plan implements a safety protocol specifying speed restrictions of the machinery in proximity to a human and a minimum separation distance between the machinery and a human. |
Claim: | 9. The method of claim 7 , wherein the corresponding cost value is assigned to each of the trajectories based also at least in part on a length of the trajectory and/or an operation time of the machinery on the trajectory. |
Claim: | 10. The method of claim 7 , further comprising the step of providing a plurality of sensors distributed about the workspace, each of the sensors being configured to record images of a portion of the workspace within a sensor field of view, the workspace portions collectively covering the entire workspace, wherein the 3D region of the workspace is computed based on images generated by the sensors during performance of the task by the machinery. |
Claim: | 11. The method of claim 10 , and further comprising the step of altering the motion plan in response to a change in the 3D region. |
Claim: | 12. The method of claim 10 , wherein the motion plan is recomputed in response to a change in the 3D region. |
Patent References Cited: | 20170087722 March 2017 Aberg et al. 20180173242 June 2018 Lalonde 20180222051 August 2018 Vu 20190105779 April 2019 Einav 20190217472 July 2019 Nakasu et al. 20190262991 August 2019 Sugiyama et al. 20190262993 August 2019 Cole et al. 20200164516 May 2020 Lehment et al. |
Other References: | International Preliminary Report on Patentability and Written Opinion of corresponding PCT Patent Application No. PCT/US20/47399 dated Feb. 17, 2022 (9 pages). cited by applicant International Search Report, Patent Application No. PCT/US2020/047399, dated Jul. 26, 2022, 10 pages. cited by applicant |
Assistant Examiner: | Neleski, Elizabeth Rose |
Primary Examiner: | Mott, Adam R |
Attorney, Agent or Firm: | Morgan, Lewis & Bockius LLP |
رقم الانضمام: | edspgr.11919173 |
قاعدة البيانات: | USPTO Patent Grants |
الوصف غير متاح. |