# US 11,908,204 B2 · Tracking articulated objects > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,908,204 B2 - Document ID: US11908204B2 - Status: Granted - Kind: B2 - Application number: 17/827,182 - Filed: 2022-05-27 - Published: 2022-11-17 - Granted: 2024-02-20 - Earliest claimed: 2020-02-28 - Assignees: Zoox, Inc. - Applicants: Zoox, Inc. - Inventors: Shiwei Sheng; Subhasis Das; Yassen Ivanchev Dobrev; Chuang Wang - Web page: https://patentgrep.com/patent/US11908204B2 ## CPC - G05D 1/0274: {using mapping information stored in a memory device (navigation using map-matching G01C21/30)} - G06V 20/58: Recognition of moving objects or obstacles, e.g. vehicles or pedestrians; Recognition of traffic objects, e.g. traffic signs, traffic lights or roads - G06T 7/277: involving stochastic approaches, e.g. using Kalman filters - G06V 10/98: Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL ## Abstract Navigation systems can identify objects in an environment and generate representations of those objects. A representation of an articulated vehicle can include two segments rotated relative to each other about a pivot, with a first segment corresponding to a first portion of the articulated vehicle and the second segment corresponding to a second portion of the articulated vehicle. The articulated object can be tracked in the environment by generating estimated updated states of the articulated agent based on previous states and/or measured states of the object using differing motion model updates for the differing portions. The estimated updated states may be determined using one or more filtering algorithms, which may be constrained using pseudo-observables. ## Claims ### Claim 1 A method comprising: determining, using a first model and a state of an articulated object, a first predicted state of a first segment of the articulated object; determining, using a second model and the state of the articulated object, a second predicted state of a second segment of the articulated object; determining, based at least in part on the first predicted state and the second predicted state, a predicted state of the articulated object; receiving sensor data; generating, based at least in part on the sensor data, a measured state of the articulated object; determining an error between the predicted state of the articulated object and the measured state of the articulated object; determining, based at least in part on the error, an updated state of the articulated object; and controlling, based at least in part on the updated state of the articulated object, an autonomous vehicle to navigate relative to the articulated object. ### Claim 2 (depends on 1) The method of claim 1, wherein the first model or the second model comprise one or more first pseudo-observables based at least in part on a first constraint associated with a pivot point about which the first segment rotates relative to the second segment. ### Claim 3 (depends on 2) The method of claim 2, wherein; the first constraint is based at least in part on a first distance and a second distance; the first distance is a distance between a first center associated with the first segment of the articulated object and the pivot point; and the second distance is a distance between a second center associated with the second segment of the articulated object and the pivot point. ### Claim 4 (depends on 2) The method of claim 2, wherein the first model comprises a second pseudo-observable based at least in part on a first non-holonomic constraint. ### Claim 5 (depends on 4) The method of claim 4, wherein the first non-holonomic constraint is based at least in part on one or more of a velocity of the first segment, a yaw of the first segment, a yaw of the second segment, a yaw rate of the first segment, extents of the first segment, or extents of the second segment. ### Claim 6 (depends on 1) The method of claim 1, wherein the first model is an extended Kalman filter. ### Claim 7 A system comprising: one or more processors; and memory storing processor-executable instructions that, when executed by the one or more processors, cause the system to perform operations comprising: receiving state information for a first portion of an articulated object and for a second portion of an articulated object; determining, based at least in part on the state information and a first model constrained according to a first pseudo-observable, a first predicted state of the first portion of the articulated object; determining, based at least in part on the state information and a second model constrained according to a second pseudo-observable, a second predicted state of the second portion of the articulated object; and determining, based at least in part on the first predicted state and the second predicted state, an updated state of the articulated object. ### Claim 8 (depends on 7) The system of claim 7, wherein the determining the updated state of the articulated object comprises: determining, using the first model and based on the first predicted state, a first updated representation of the first portion of the articulated object; and determining, using the second model and based on the second predicted state, a second updated representation of the second portion of the articulated object. ### Claim 9 (depends on 7) The system of claim 7, wherein the state information comprises: first pose information including at least one of a first center of a first previous representation, one or more first dimensions associated with the first previous representation, a first yaw angle of the first previous representation, or a first yaw rate of the first previous representation; and second pose information including at least one of a second center of the second previous representation, one or more second dimensions associated with the second previous representation, or a second yaw angle of the second previous representation, a second yaw rate of the second previous representation. ### Claim 10 (depends on 7) The system of claim 7, wherein the first model or the second model comprise one or more pseudo-observables based at least in part on a constraint associated with a pivot point about which the first segment rotates relative to the second segment. ### Claim 11 (depends on 10) The system of claim 10, wherein: the constraint is based at least in part on a first distance and a second distance; the first distance is a distance between a first center associated with the first segment of the articulated object and the pivot point; and the second distance being a distance between a second center associated with the second segment of the articulated object and the pivot point. ### Claim 12 (depends on 7) The system of claim 7, wherein the first model comprises a first pseudo-observable based at least in part on a first non-holonomic constraint or the second model comprises a second pseudo-observable based at least in part on a second non-holonomic constraint. ### Claim 13 (depends on 12) The system of claim 12, wherein: the first model comprises the first pseudo-observable based at least in part on the first non-holonomic constraint; and the first non-holonomic constraint is based at least in part on a velocity of the first segment, a yaw of the first segment, and extents of the first segment. ### Claim 14 (depends on 12) The system of claim 12, wherein: the second model comprises the second pseudo-observable based at least in part on the second non-holonomic constraint, and the second non-holonomic constraint is based at least in part on a velocity of the first segment, a yaw of the first segment, a yaw of the second segment, a yaw rate of the first segment, extents of the first segment, and extents of the second segment. ### Claim 15 (depends on 7) The system of claim 7, the operations further comprising: determining, based on the first predicted state and the second predicted state, a predicted state of the articulated object; receiving sensor data; determining, based on the sensor data, a measured state of the articulated object; and determining an error between the predicted state and the measured state. ### Claim 16 (depends on 15) The system of claim 15, wherein the error comprises at least one of a Euclidian distance between centers, an angular difference between yaw angles, or an intersection over union. ### Claim 17 One or more non-transitory computer readable media storing instructions that, when executed by one or more processors, cause a computing device to perform operations comprising: determining, using a first model and a state of an articulated object, a first predicted state of a first segment of the articulated object; determining, using a second model and the state of the articulated object, a second predicted state of a second segment of the articulated object; determining, based at least in part on the first predicted state and the second predicted state, a predicted state of the articulated object; receiving sensor data; generating, based at least in part on the sensor data, a measured state of the articulated object; determining an error between the predicted state of the articulated object and the measured state of the articulated object; determining, based at least in part on the error, an updated state of the articulated object; and controlling, based at least in part on the updated state of the articulated object, an autonomous vehicle to navigate relative to the articulated object. ### Claim 18 (depends on 17) The one or more non-transitory computer readable media of claim 17, wherein the first model or the second model comprise one or more pseudo-observables based at least in part on a constraint associated with a pivot point about which the first segment pivots relative to the second segment. ### Claim 19 (depends on 17) The one or more non-transitory computer readable media of claim 17, wherein the first model comprises a first pseudo-observable based at least in part on a first non-holonomic constraint. ### Claim 20 (depends on 19) The one or more non-transitory computer readable media of claim 19, wherein at least one of the first non-holonomic constraint is based at least in part on one or more of a velocity of the first segment, a yaw of the first segment, a yaw of the second segment, a yaw rate of the first segment, extents of the first segment, and extents of the second segment.