Find new failures as robot policies and controllers evolve. Compare reference and candidate runs, inspect evidence, and bring evaluation into your development workflow.
Ingest each robot trial as a Motion Session with a robot entity and telemetry sources (CSV, JSON, or ROS2 bags via ros-bridge). Call POST /v1/motionbench/evaluations with the reference and candidate session IDs. Inspect metrics, anomaly events and series. Iterate the policy, then evaluate again against the same reference.
MotionBench for evaluation. Arisole Fusion for multimodal context. Motion API for sessions and ingest. StrideIQ is the human product and is not a robot controller.
See robot regression testing in action. Inject a failure and watch MotionBench identify where physical behaviour changes. Open /break.
Wire CI/CD through /robot-ci-cd and /developers. Explore world-model research at /world-model-assurance and public evidence at /benchmarks.
Keep a frozen reference run and surface when trajectory deviation or anomalies jump.
Compare walking controllers on smoothness and velocity stability with shared evidence.
When telemetry is incomplete, evaluations mark what cannot be compared instead of inventing values.
Share evaluation IDs so research and controls review the same evidence.
Recorded or ingested robot motion sessions with reference and candidate runs.
Yes. Convert bags with the offline ros-bridge into Motion API sessions, then evaluate those sessions in MotionBench.
Start with /developers for session contracts, then /motionbench and /robot-ci-cd for evaluation workflows.
Loading Arisole. If the interactive app does not start, continue with the public links above.