{"uid":"cap_5AOIRnjmKYu0aMUCyOSTQ","slug":"rqm-estimate-fused-state-c17c6538","name":"RQM Estimate Fused State","description":"Problem: Fuse these bounded synchronized sensor observations under the supplied diagonal uncertainty model and rules. Input: JSON with observations, model, rules. Result: fused state, diagonal covariance, sensor residuals and verdict. Limits: Software/model evidence only; 65536 request bytes; 5 s execution.","url":"https://jobs.rqmtechnologies.com/x402/buyer-jobs/robotics.estimate-fused-state.v1","method":"POST","headers":{},"bodySchema":{"type":"object","properties":{"request":{"type":"object","title":"FusedStateRequest","required":["observations","model","rules"],"properties":{"model":{"enum":["independent_diagonal_gaussian","correlated_gaussian"],"type":"string","title":"Model"},"rules":{"type":"object","title":"FusionRules","required":["maximum_time_skew_s","maximum_normalized_residual"],"properties":{"maximum_time_skew_s":{"type":"number","title":"Maximum Time Skew S","maximum":60,"minimum":0},"maximum_normalized_residual":{"type":"number","title":"Maximum Normalized Residual","maximum":1000000,"minimum":0}},"additionalProperties":false},"observations":{"type":"array","items":{"type":"object","title":"SensorObservation","required":["sensor_id","timestamp_s","values","variances"],"properties":{"values":{"type":"array","items":{"type":"number"},"title":"Values","maxItems":12,"minItems":1},"sensor_id":{"type":"string","title":"Sensor Id","pattern":"^[A-Za-z0-9._-]{1,64}$"},"variances":{"type":"array","items":{"type":"number"},"title":"Variances","maxItems":12,"minItems":1},"covariance":{"anyOf":[{"type":"array","items":{"type":"array","items":{"type":"number"}},"maxItems":12},{"type":"null"}],"title":"Covariance","default":null},"timestamp_s":{"type":"number","title":"Timestamp S","maximum":86400,"minimum":0}},"additionalProperties":false},"title":"Observations","maxItems":64,"minItems":2}},"additionalProperties":false},"schema_version":{"const":"rqm.jobs.bazaar-buyer-job-request.v1"},"idempotency_key":{"type":"string","pattern":"^[A-Za-z0-9][A-Za-z0-9._:-]*$","maxLength":128,"minLength":1},"max_total_price":{"type":"string","pattern":"^(?:0|[1-9]\\d{0,13})(?:\\.\\d{1,6})?$"}}},"responseSchema":null,"example":null,"exampleRequest":null,"tags":["x402"],"displayCostAmount":"0.01","displayCostAsset":"USDC","priceDynamic":false,"priceHint":null,"priceStatus":"priced","priceSource":"probe","requiresHandshake":false,"reviewCount":0,"rating":{"score":"0.00","successRate":"0.00","reviews":0,"stars":null,"state":"unrated"},"availabilityStatus":"unknown","priceObserved":null,"sessionDeposit":null,"pricing":{"kind":"static","summary":"$0.01/call","primary":{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"},"accepted":[{"kind":"static","protocol":"x402","network":"base","amountUsd":"0.01","per":"call","confidence":"exact"}]},"paymentMethods":[{"uid":"pm_HuHo_Aq2anFzMhBQEPJ7g","protocol":"x402","methodType":"crypto","chain":"base","mode":"charge","costAmount":"0.01","costPer":"request","priority":0,"asset":"0x833589fCD6eDb6E08f4c7C32D4f71b54bdA02913","unit":"request","depositMicros":null,"planRef":null}],"brandName":null,"brandSlug":null,"brandBaseUrl":null,"brandDocsUrl":null,"whatItDoes":"Fuses multiple synchronized sensor observations into a single state estimate using an independent diagonal Gaussian uncertainty model with configurable time-skew and residual bounds.","exampleAgentPrompt":"Fuse these two synchronized sensor readings — GPS (values [37.77, -122.41], variances [0.001, 0.001], timestamp 12.5s, sensor_id 'gps.primary') and wheel odometry (values [37.771, -122.412], variances [0.005, 0.005], timestamp 12.48s, sensor_id 'odom.left') — using the independent_diagonal_gaussian model with a max time skew of 0.1 seconds and max normalized residual of 50.","exampleUseCases":[{"title":"Robot localization from GPS and odometry","prompt":"Fuse my robot's GPS reading (values [1.23, 4.56, 0.0], variances [0.01, 0.01, 0.001], timestamp 30.0s, sensor_id 'gps.main') with wheel odometry (values [1.22, 4.55, 0.0], variances [0.02, 0.02, 0.001], timestamp 29.95s, sensor_id 'odom.rear') using independent_diagonal_gaussian, max time skew 0.1s, max normalized residual 100."},{"title":"IMU and magnetometer attitude fusion","prompt":"Combine my IMU orientation output (values [0.01, -0.02, 0.98], variances [0.0001, 0.0001, 0.0001], timestamp 5.0s, sensor_id 'imu.0') with magnetometer heading (values [0.01, -0.021, 0.979], variances [0.001, 0.001, 0.001], timestamp 4.99s, sensor_id 'mag.0') into a fused attitude estimate — use independent_diagonal_gaussian, max time skew 0.05s, max normalized residual 25."},{"title":"Multi-lidar distance state estimation","prompt":"Fuse three lidar distance sensors: front (values [2.1], variances [0.01], timestamp 10.0s, sensor_id 'lidar.front'), left (values [1.8], variances [0.015], timestamp 10.01s, sensor_id 'lidar.left'), and rear (values [3.4], variances [0.012], timestamp 9.99s, sensor_id 'lidar.rear') using independent_diagonal_gaussian with max time skew 0.05s and max normalized residual 200."}],"resultDescription":"Returns a fused state vector along with associated fused variances, computed by combining all valid sensor observations under the independent diagonal Gaussian model. Also includes diagnostics indicating which observations passed the time-skew and normalized-residual checks, and which were rejected as outliers.","failureModes":["Observations with timestamps exceeding maximum_time_skew_s relative to each other are rejected or cause fusion failure","Normalized residuals above maximum_normalized_residual cause observation rejection or error","Fewer than 2 valid observations after filtering results in an insufficient-data error","Mismatched values/variances array lengths cause validation errors","sensor_id not matching the pattern ^[A-Za-z0-9._-]{1,64}$ causes a schema validation error","Providing only 1 observation (minItems:2 not met) results in a request validation failure","Timestamp outside [0, 86400] range causes schema rejection","Values or variances arrays with more than 12 items are rejected"],"whenToPreferThis":"Use this endpoint when you have two or more synchronized sensor observations with known, explicitly specified per-dimension variances (diagonal covariance), frames are already aligned, and time skew between sensors is bounded and small. It is ideal for robotics state estimation pipelines (localization, attitude, velocity) where sensors are pre-synchronized and noise is modeled as independent Gaussian per axis. Prefer alternatives when full covariance matrices are needed, when sensors are not time-aligned, or when you need to model cross-axis correlations.","instructions":null,"reviewSummary":null,"reviewSummaryHighlights":null,"reviewSummaryConcerns":null,"reviewSummaryGeneratedAt":null,"activationCount":0,"lastUsedAt":null,"lastSuccessfullyRanAt":null,"lastHealthCheckAt":"2026-09-16T06:33:33.711Z","isFirstParty":false}