Cite the exact evidence you used.

RCI Robot Component Evidence Catalog

120 exact products, 55 catalog-linked manufacturer profiles and 1,205 claim-level records. The 17-record actuation depth wave adds quasi-direct-drive joint modules, bus-servo variants, strain-wave and cycloidal reducers, frameless torque motors and servo drives, including first records from five Chinese manufacturers; every value remains a conditioned manufacturer claim with explicit unknowns and zero RCI physical tests. The release supports 20 row-level Robot-to-Component crosswalks; these are not as-built, compatibility or physical-test claims. Cite a component page as well when relying on a model-specific claim.

Suggested citationRobot Component Index. “RCI Robot Component Evidence Catalog.” version 0.4.15, 2026-08-19. https://robotcomponentindex.com/data/

RCI Source Intelligence Directory

101 monitored channels with source type, access, monitoring and reuse-guidance fields. Release v0.1.5 promotes the official ROBOTIS DynamixelSDK and NVIDIA Isaac ROS Common Atom feeds, bringing the public directory to 74 primary channels and 21 direct monitor endpoints. Inclusion is not blanket republication permission or independent validation.

Suggested citationRobot Component Index. “RCI Source Intelligence Directory.” version 0.1.5, 2026-08-19. https://robotcomponentindex.com/sources/

3D LiDAR Range Claims: 9 Sensors, 21 Conditioned Values

Target-reflectivity and stated-condition observations; not a cross-brand performance ranking.

Suggested citationRobot Component Index. “3D LiDAR Range Claims: 9 Sensors, 21 Conditioned Values.” RCI 014, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/3d-lidar-range-claims-audit/

Robot Actuator Torque Claims: 18 Records, 5 Duty Boundaries

Preserves continuous, rated, calculated-continuous, stall and peak-only boundaries; ratios are within-model only.

Suggested citationRobot Component Index. “Robot Actuator Torque Claims: 18 Records, 5 Duty Boundaries.” RCI 015, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/continuous-torque-claims-audit/

Robot Actuator Backlash Claims: 18 Records, 15 Statements, 0 Complete Test Methods

Backlash, lost motion, transmission error, accuracy and repeatability remain separate metrics.

Suggested citationRobot Component Index. “Robot Actuator Backlash Claims: 18 Records, 15 Statements, 0 Complete Test Methods.” RCI 016, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/actuator-backlash-claims-audit/

Depth-Camera Error Claims: 11 Records, 16 Selected Values, 0 Complete Reproduction Packages

Separates range labels and error metrics by mode, lens, distance and disclosed method.

Suggested citationRobot Component Index. “Depth-Camera Error Claims: 11 Records, 16 Selected Values, 0 Complete Reproduction Packages.” RCI 017, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/depth-camera-accuracy-claims-audit/

Robot Edge Compute: 17 Records, 9 Numeric TOPS Claims, 0 Software Support End Dates

Keeps production modules, development platforms and complete systems on separate hardware boundaries.

Suggested citationRobot Component Index. “Robot Edge Compute: 17 Records, 9 Numeric TOPS Claims, 0 Software Support End Dates.” RCI 018, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/robot-edge-compute-claims-audit/

Robot Battery Compatibility: 11 Records, 8 Packs, 0 Complete Drop-In Evidence Packages

Separates pack, cell, connector, communication, charger, temperature, mechanical and compliance boundaries.

Suggested citationRobot Component Index. “Robot Battery Compatibility: 11 Records, 8 Packs, 0 Complete Drop-In Evidence Packages.” RCI 019, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/robot-battery-compatibility-audit/

Robot Joint Backlash Test Protocol: 3 Boundaries, 3 Positions, 5 Recorded Cycles

Public draft RCI-BLM-1; physical fixture validation and cross-laboratory round-robin remain required.

Suggested citationRobot Component Index. “Robot Joint Backlash Test Protocol: 3 Boundaries, 3 Positions, 5 Recorded Cycles.” RCI 020, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/reproducible-backlash-lost-motion-test-protocol/

Status: public draft; laboratory validation required.

Open-Source Robot BOM Evidence: 5 Platforms, 4 Commit-Pinnable Lists, 0 Complete Rebuild Packages

The 207 total is selected source rows or list items, not unique parts or a platform-complexity ranking.

Suggested citationRobot Component Index. “Open-Source Robot BOM Evidence: 5 Platforms, 4 Commit-Pinnable Lists, 0 Complete Rebuild Packages.” RCI 021, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/open-source-robot-bom-evidence-audit/

Robot Component Specification Drift: 9 Field Differences Across 7 Products

Only two Ouster fields have a public product-generation boundary; seven other observations remain documentation conflicts.

Suggested citationRobot Component Index. “Robot Component Specification Drift: 9 Field Differences Across 7 Products.” RCI 022, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/component-datasheet-version-drift-report/

Robot Component Catalog Delta: 35 Added Claims, 5 New Independent Records, 0 Removed IDs

Same 75-component cohort; this is a claim-depth and revision audit, not evidence of product, shipment or market growth.

Suggested citationRobot Component Index. “Robot Component Catalog Delta: 35 Added Claims, 5 New Independent Records, 0 Removed IDs.” RCI 023 / Data Brief 002, research dataset version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/catalog-release-delta-data-brief/

Can Four Robot Components Form One Stack? 30 Interface Checks, 0 Full-Stack Validations

Four exact products and five interface paths; v0.2.0 adds the RealSense v2.58.3 beta and firmware-table boundary, but documented matches remain design inputs rather than exact-pair tests or a full-stack compatibility conclusion.

Suggested citationRobot Component Index. “Can Four Robot Components Form One Stack? 30 Interface Checks, 0 Full-Stack Validations.” RCI 024, version 0.2.0, 2026-08-10. https://robotcomponentindex.com/research/exact-model-robot-stack-interface-audit/

Robot Battery and Actuator Telemetry: Two 4.3-Hour Traces, One Unloaded Boundary

Two unloaded public traces; 10 Hz grid density and descriptive battery–motion association do not establish BMS bandwidth, causal actuator energy, payload efficiency or battery endurance.

Suggested citationRobot Component Index. “Robot Battery and Actuator Telemetry: Two 4.3-Hour Traces, One Unloaded Boundary.” RCI 025, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/robot-battery-actuator-telemetry-audit/

KUKA Motor-Current Payload Dataset: 128 Files, 685,400 Rows, One Timing Conflict

Structural audit of 128 public CSV files; paper-reported MLP metrics are not independently reproduced, and the deposited Sample sequence remains in unresolved conflict with the stated 12 ms cadence.

Suggested citationRobot Component Index. “KUKA Motor-Current Payload Dataset: 128 Files, 685,400 Rows, One Timing Conflict.” RCI 026, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/kuka-motor-current-payload-dataset-audit/

LT-PAM Open-Hardware Audit: Nine Files, Three Versions, Zero Raw Test Traces

Integrity, version, BOM and mesh-topology audit of a nine-file open-hardware deposit; author-reported force, contraction, rupture, cost and durability claims are not independently reproduced.

Suggested citationRobot Component Index. “LT-PAM Open-Hardware Audit: Nine Files, Three Versions, Zero Raw Test Traces.” RCI 027, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/lt-pam-open-hardware-reproducibility-audit/

L99BM114 BMS Evidence: 159 Datasheet Pages, Two Transient Plots, Zero Raw Traces

Exact-model public-evidence audit; two ST-authored transient plots are not independent tests, and no public raw trace or complete acquisition method was found in the cited surfaces.

Suggested citationRobot Component Index. “L99BM114 BMS Evidence: 159 Datasheet Pages, Two Transient Plots, Zero Raw Traces.” RCI 028, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/l99bm114-bms-evidence-audit/

RAVEN II Force Actuation Evidence: 6 Motor-Cable Units, 3 Axis MAEs, 0 Released Dataset Files

Public-package audit of arXiv:2608.06488 v1; the three per-axis MAEs are author-reported and not independently recomputed, while the public source bundle contains no dataset, controller code, CAD or BOM files.

Suggested citationRobot Component Index. “RAVEN II Force Actuation Evidence: 6 Motor-Cable Units, 3 Axis MAEs, 0 Released Dataset Files.” RCI 029, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/raven-ii-force-actuation-evidence-audit/

S-HASEL Actuator Evidence: 20 µm Films, 1.2 mL Fill, Zero MRI Tests

Public-evidence audit of Research Square preprint rs-10623292 v1; all NRMSE values are author-reported and not recomputed, while closed-loop control, the integrated biopsy robot, needle puncture and MRI compatibility remain untested.

Suggested citationRobot Component Index. “S-HASEL Actuator Evidence: 20 µm Films, 1.2 mL Fill, Zero MRI Tests.” RCI 030, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/s-hasel-actuator-evidence-audit/

DepthAI Core 3.8.0 Evidence: 3 Assets, 3 Hash Matches, 0 Device Benchmarks

Release-integrity and disclosure audit of DepthAI Core v3.8.0; three GitHub asset hashes were independently matched, but RCI did not execute the software or validate device accuracy, latency, power, calibration, compatibility or stability.

Suggested citationRobot Component Index. “DepthAI Core 3.8.0 Evidence: 3 Assets, 3 Hash Matches, 0 Device Benchmarks.” RCI 031, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/depthai-3-8-release-evidence-audit/

Ouster SDK 1.0.0 Evidence: 36 PyPI Files, One Verified sdist, Zero Sensor Benchmarks

Release-integrity and disclosure audit of Ouster SDK v1.0.0; the PyPI sdist hash was independently matched, but RCI did not execute the SDK or validate LiDAR range, accuracy, latency, throughput, mapping quality, power, thermal behavior, compatibility or stability.

Suggested citationRobot Component Index. “Ouster SDK 1.0.0 Evidence: 36 PyPI Files, One Verified sdist, Zero Sensor Benchmarks.” RCI 032, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/ouster-sdk-1-0-release-evidence-audit/

Ryzen AI Software 1.8 Evidence: 8 LLM/VLM Additions, One RTF Claim, Zero Robot Benchmarks

Release-integrity and disclosure audit of AMD Ryzen AI Software v1.8.0; RCI verified public source identity and generated-archive structure but did not accept EULA terms, download runtime packages or LFS objects, execute software, access Ryzen AI hardware or validate a robot workload.

Suggested citationRobot Component Index. “Ryzen AI Software 1.8 Evidence: 8 LLM/VLM Additions, One RTF Claim, Zero Robot Benchmarks.” RCI 033, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/ryzen-ai-1-8-release-evidence-audit/

foxBMS 2 v1.11.0 Evidence: 2,822 Files, 93 Changelog Bullets, Zero Published HIL Files

Release-integrity and disclosure audit of foxBMS 2 v1.11.0; RCI verified public source identity and generated-archive structure but did not execute tests, obtain unpublished HIL material, download linked hardware packages or validate a BMS, battery or robot system.

Suggested citationRobot Component Index. “foxBMS 2 v1.11.0 Evidence: 2,822 Files, 93 Changelog Bullets, Zero Published HIL Files.” RCI 034, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/foxbms-1-11-release-evidence-audit/

Livox SDK2 v1.3.1 Evidence: 221 Files, 6 Sample Targets, Zero Test Paths

Release-integrity and disclosure audit of Livox SDK2 v1.3.1; RCI matched generated source archives to the fixed tree and inspected Mid-360S code surfaces but did not compile or execute software, download firmware, access a LiDAR or validate performance, timing, compatibility, stability or robot integration.

Suggested citationRobot Component Index. “Livox SDK2 v1.3.1 Evidence: 221 Files, 6 Sample Targets, Zero Test Paths.” RCI 035, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/livox-sdk2-1-3-1-release-evidence-audit/

RealSense SDK 2.58.3 Evidence: 8 Assets, 28 Successful Checks, Zero RCI Camera Tests

Release-integrity and disclosure audit of RealSense SDK 2.0 v2.58.3; RCI matched two generated source archives, all eight uploaded asset hashes and public CI metadata but did not execute binaries, build or install software, update firmware, connect a camera or validate depth, vision, compatibility or robot performance.

Suggested citationRobot Component Index. “RealSense SDK 2.58.3 Evidence: 8 Assets, 28 Successful Checks, Zero RCI Camera Tests.” RCI 036, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/realsense-sdk-2-58-3-release-evidence-audit/

Six Robot Software Releases: 1,992 Test-Surface Paths, 32 Successful Public Checks, Zero RCI Device Tests

Cross-release synthesis of six immutable vision, LiDAR, main-compute and battery-management software audits. Test-surface path counts, public checks and digest matches remain distinct from physical-device tests, robot validation and performance rankings.

Suggested citationRobot Component Index. “Six Robot Software Releases: 1,992 Test-Surface Paths, 32 Successful Public Checks, Zero RCI Device Tests.” RCI 037, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/non-joint-robot-release-evidence-matrix/

Where Robot Component Intelligence Comes From: 96 Channels, 69 Primary Sources, Five Reuse Classes

Aggregate atlas of source groups, hardware-layer coverage, direct monitoring and conservative reuse classes derived from source-directory v0.1.2. Inclusion, primary status and network reachability do not grant blanket republication rights or independent-validation status.

Suggested citationRobot Component Index. “Where Robot Component Intelligence Comes From: 96 Channels, 69 Primary Sources, Five Reuse Classes.” RCI 038, version 0.1.0, 2026-08-10. https://robotcomponentindex.com/research/robot-component-industry-source-atlas/

Orbbec SDK 2.9.3 Evidence: 12 Hash Matches, 0 Public Checks, One Unresolved License Boundary

Release-integrity, provenance, disclosure and rights-boundary audit of Orbbec SDK v2.9.3. RCI matched twelve uploaded asset sizes and SHA-256 digests and both generated source archives, but executed no software or model, accessed no device, found no public checks at the tag and did not resolve conflicting extension-license wording or model rights.

Suggested citationRobot Component Index. “Orbbec SDK 2.9.3 Evidence: 12 Hash Matches, 0 Public Checks, One Unresolved License Boundary.” RCI 039, version 0.1.0, 2026-08-11. https://robotcomponentindex.com/research/orbbec-sdk-2-9-3-release-evidence-audit/

EsaacSim Event-Camera Simulation: 5 Resolutions, 6.98–29.16 ms Backend Time, Zero Real-Sensor Comparisons

Fixed-paper evidence brief for arXiv:2608.08522v1. Author-reported event-generation backend timing and allocated GPU memory are separated from excluded rendering and communication overhead, absent real-camera and robot-task comparisons, zero RCI execution and unresolved public-code availability.

Suggested citationRobot Component Index. “EsaacSim Event-Camera Simulation: 5 Resolutions, 6.98–29.16 ms Backend Time, Zero Real-Sensor Comparisons.” RCI 040, version 0.1.0, 2026-08-11. https://robotcomponentindex.com/research/esaacsim-event-camera-simulation-evidence-brief/

Ouster Q2 2026 LiDAR Supply Signal: >17,000 Sensor Units, ~53% LiDAR, Zero Model-Level Split

Facts-first review of Ouster’s Q2 2026 10-Q and earnings exhibit. Company-reported combined lidar/camera units, approximate lidar mix, GAAP values, supplier commitments and roadmap status remain separate from exact model quantities, market share, independent product validation and zero RCI device testing.

Suggested citationRobot Component Index. “Ouster Q2 2026 LiDAR Supply Signal: >17,000 Sensor Units, ~53% LiDAR, Zero Model-Level Split.” RCI 041, version 0.1.0, 2026-08-11. https://robotcomponentindex.com/research/ouster-q2-2026-lidar-supply-signal/

ST Q2 2026 Non-Joint Supply Signal: P&D +19.2% QoQ, Two 200 mm SiC Ramps, Zero Exact Robot-Component Split

Facts-first review of STMicroelectronics’ Q2 2026 6-K. Company and segment financial signals, two 200 mm SiC manufacturing starts and one acquisition boundary remain separate from robot revenue, exact product demand, capacity, yield, procurement conclusions and zero RCI hardware testing.

Suggested citationRobot Component Index. “ST Q2 2026 Non-Joint Supply Signal: P&D +19.2% QoQ, Two 200 mm SiC Ramps, Zero Exact Robot-Component Split.” RCI 042, version 0.1.0, 2026-08-11. https://robotcomponentindex.com/research/st-q2-2026-non-joint-supply-signal/

CDPR Actuator-Level Policy Evidence: 4-Cable Simulation to One 8-Motor Robot, Zero RCI Runs

Facts-first paper review of a shared actuator-level CDPR policy. Selected four/eight-cable simulation and one author-reported eight-motor physical trajectory remain separate from arbitrary-configuration validation, exact component identity, repeatable raw evidence and zero RCI simulation or hardware execution.

Suggested citationRobot Component Index. “CDPR Actuator-Level Policy Evidence: 4-Cable Simulation to One 8-Motor Robot, Zero RCI Runs.” RCI 043, version 0.1.0, 2026-08-11. https://robotcomponentindex.com/research/cdpr-actuator-level-policy-evidence/

AMD Kria AI Claims Audit: Four Benchmark Footnotes, Zero RCI Hardware Runs

Claim-level provenance audit of AMD Kria AI launch surfaces. Family descriptions and four headline metrics remain separate from an orderable exact-model identity, a matched Kria AI SOM benchmark and zero RCI hardware execution.

Suggested citationRobot Component Index. “AMD Kria AI Claims Audit: Four Benchmark Footnotes, Zero RCI Hardware Runs.” RCI 044, version 0.1.0, 2026-08-11. https://robotcomponentindex.com/research/amd-kria-ai-claims-audit/

Robot Component Source Directory Delta: 101 Channels, 74 Primary Sources, 21 Direct Monitors

EV3 recomputation of immutable source-directory v0.1.2 to v0.1.5. Five manufacturer-maintained release monitors and their layer, primary and rights-class deltas remain separate from independent validation, endpoint uptime and blanket republication permission.

Suggested citationRobot Component Index. “Robot Component Source Directory Delta: 101 Channels, 74 Primary Sources, 21 Direct Monitors.” RCI 045, version 0.1.0, 2026-08-11. https://robotcomponentindex.com/research/robot-component-source-directory-delta-audit/