Back to News & Insights
Frontier Observations

HaMeR / MANO × Smart Home Installation: TOBI Wrist Egocentric Capture Scenario Acceptance

Against the public HaMeR / MANO specifications, this outlines visibility, hardware synchronization, and failure-sample retention for smart-home installation tasks. It explains how the wrist turns the paper's fields into an auditable capture sheet without implying that TO

2026-09-08
Chief News Officer, TOBI Technology
Frontier Observations
HaMeR / MANO × Smart Home Installation: TOBI wrist egocentric capture scenario acceptance (152)
Chief Insights Research Frontiers 2026-09-13 Chinese original: about 5044 characters

Market & Solutions Perspective | 2026-09-13

Around 2026-09-13, the question customers ask most is not whether a paper exists, but whether devices and data can be accepted according to the HaMeR / MANO criteria. The public claim is: a monocular hand mesh reconstruction lineage, with hard thresholds on egocentric hand pixel quality. TOBI's role is to list wrist as a deliverable field in the quote request, not to imply exclusive data assets.

Benchmarking against the public HaMeR / MANO specifications, sort out visibility, hard synchronization, and failure-sample retention in smart-home installation tasks. Explain how wrist turns paper fields into auditable collection forms, without implying that TOBI owns this dataset. For teams planning Ego datasets, VLA training, and robot transfer around 2026, emphasize auditable delivery, versioned calibration, and hard-synchronization quality checks, and avoid misreading public benchmarks as any single company's exclusive capability.

Live demo demo-hero-e6
Live demo animation (demo-hero-e6.webp): shows the wrist recording pipeline for comparison against HaMeR / MANO public specifications; not official paper material.

What the Paper Timeline Tells Us

Around 2024, HaMeR / MANO pushed the community discussion toward a clear question: the monocular hand mesh reconstruction lineage sets a hard threshold for egocentric hand pixel quality. The timeline tells us that the value of public benchmarks lies in defining "what counts as a qualified first-person/embodied sample," not in implying that any hardware vendor automatically possesses data assets of equivalent scale. TOBI cites this paper solely for specification comparison and procurement language translation.

If HaMeR / MANO is included in the 2026-09-13 procurement review, three layers should be distinguished: the timing of the paper's release and open-source links, the timing of community reproduction and secondary annotation, and the timing when enterprise-built/procured data actually enters the database. Method iterations between 2024 and 2026 often occur across these three layers; what hardware teams should track is field/schema changes, not chasing paper titles.

For scene-type tasks (this article's slug: news-seo-152-scene-wrist-智能-s080), the paper timeline also indicates when "failure samples and long-tail scenarios" were written into the benchmark protocol. Constraints that appear later often affect VLA training more than early scale numbers; device selection should reserve the ability to retain time windows before and after contact.

Dataset Boundary Statement

The HaMeR / MANO referenced in this article and its link https://arxiv.org/abs/2312.06551 are both in a public research context; TOBI does not claim ownership, hosting, or exclusive distribution of this dataset.

HaMeR / MANO × Smart Home Installation: TOBI wrist egocentric capture scenario acceptance (152)
Figure 1 | HaMeR / MANO × smart home installation: TOBI w… corresponds to the wrist on the actual device and wearing reference (not official HaMeR / MANO material).

Acceptable requirements for capture hardware

Translating HaMeR / MANO's one-line claim into procurement language starts with defining "acceptable fields" rather than restating that the monocular hand mesh reconstruction lineage sets a hard threshold for egocentric hand pixel quality. Hardware acceptance must be independently reproducible by third parties: given fixed firmware, a fixed calibration package, and a fixed recording script, anyone can export the same timeline semantics.

  • Hard synchronization: whether each camera/IMU/gesture stream shares an acceptable clock domain (target jitter and measured distribution are recorded in the data card).
  • Calibration: intrinsic and extrinsic parameters, along with model versions such as Kannala-Brandt, are frozen with the firmware; changing the camera, ring, or wrist unit requires regression testing.
  • Container: frame timestamp units and dropped-frame markers in dual-stream HEVC/fMP4 or MCAP and similar formats must not be lost during transcoding.
  • Sharding: shard duration for long-horizon dex/collaborative tasks, ~5 GB upload limits, and DatasetServer health checks.
  • Failure samples: whether contact-invisible, occluded, and desynced segments are retained and labeled rather than silently deleted.
  • Compliance: operator authorization, site permissions, and de-identification policies are included as delivery attachments; unrelated to the licensing of publicly released academic datasets.

The following sequence is suitable for the marketing team to write into an SOP (2026-09-13 version), bound to the wrist evaluation prototype:

  1. Freeze the wrist firmware and SDK versions; reproduce the minimal script set for the HaMeR / MANO comparison experiments.
  2. Bench sync testing: measure cross-path offset using LED / mechanical triggers to produce a baseline report.
  3. Worn-state spot check: sample 50 contact-frame multi-view consistency segments across scenes tagged wrist, HaMeR / MANO, smart home installation, scene.
  4. Ingestion QC: outputs sync_health, drop_frame, and calib_version fields.
  5. Training feedback: compare contact success rates using the hard-sync subset versus the soft-alignment subset, and record the results in the procurement review.
HaMeR / MANO × Smart Home Installation: TOBI wrist egocentric capture scenario acceptance (152)
Figure 2 | Multi-view/scenario diagram for comparing HaMeR / MANO's task density and visibility assumptions.

Mapped to TOBI wrist product capabilities

The TOBI wrist camera shares the same time domain as the head-mounted unit via PPS hardware synchronization and a UART link, filling in contact blind spots and hand-object detail; when networking with E6, the extrinsic calibration version, donning repeatability, and failed-sample retention strategy should be clearly documented.

Benchmarked against HaMeR / MANO: the monocular hand mesh reconstruction lineage sets hard thresholds for Ego hand pixel quality. On the device side, this should be translated into clickable product fields—such as frame rate / exposure / IMU frequency, whether on-device SLAM serves as a trajectory prior, and whether gesture / ring / wrist modules share a common time base. Readers should check the README and delivery package at /product-e6.html and /docs.html#device-sdk rather than assuming that paper configurations equal factory defaults.

When pillar=scene and the primary offering is wrist, it is recommended to split "paper metrics" into Must (do not purchase without them) and Stretch (R&D co-creation). Must typically covers hard synchronization, calibration version, and recording container time semantics; Stretch may cover motion capture bridging, ten-channel expansion, or cross-lab matrixing.

  • E2 spec: binocular global shutter, reconstruction-friendly offline processing, lightweight human-demo front-end (still usable as a secondary network node when this article primarily recommends wrist).
  • E6 specification: six channels + on-board SLAM + gesture recognition; host time-stamping and sharded upload are the primary solutions for dex/collaborative Ego.
  • E8 specification: ten-channel sensor density + TOF + motion capture (R&D-phase target, subject to written confirmation). An R&D target suitable for high-density sensing and VIO comparison experiments; commercial confirmation of mass-production boundaries is required.
  • Wrist: PPS + UART, in the same domain as the head-mounted unit, serving contact blind spots for ActiveUMI-type use cases.
  • Light ring / finger ring: supplementary tool-side geometry for HaMeR / MANO-friendly annotation.
HaMeR / MANO × Smart Home Installation: TOBI wrist egocentric capture scenario acceptance (152)
Figure 3 | The wrist's appearance as shown on the product page, allowing readers to jump to /product-e6.html to verify specifications.

Engineering deep dive: turning paper metrics into gates by scenario

(Deep dive · 152-1) On HaMeR / MANO and wrist: lighting variation in kitchen/home long-tail scenes requires exposure strategy to be written into the SOP; fixed/manual/adaptive must be consistent. Under the scene pillar, this directly relates to the delivery risk of "HaMeR / MANO × smart home install…".

(Deep dive · 152-2) On HaMeR / MANO and wrist: if 60fps stereo is mixed with 30fps secondary streams, downsampling and phase rules must be clearly specified. Under the scene pillar, this directly relates to the delivery risk of "HaMeR / MANO × smart home install…".

(Deep Dive · 152-3) For HaMeR / MANO and wrist: when aligning 200Hz IMU with video frames, you should specify whether interpolation or nearest-neighbor is used, as well as how boundary frames are handled. Under the scene pillar, this directly relates to the delivery risk of "HaMeR / MANO × Smart Home Sec...".

(Deep dive · 152-4) On HaMeR / MANO and wrist: ORB-SLAM3-class VIO baselines emphasize multi-sensor timestamps; egocentric devices should align to equivalent semantics. Under the scene pillar, this directly relates to the delivery risk of "HaMeR / MANO × smart home install…".

(Deep dive · 152-5) For HaMeR \ / MANO and wrist: Open X-Embodiment emphasizes cross-embodiment action distributions; the Ego field schema should reserve embodiment_id. Under the scene pillar, this directly relates to the delivery risk of "HaMeR \ / MANO × smart home secur...".

(Deep dive · 152-6) On HaMeR / MANO and wrist: DROID-class robot data lacks human priors; the lightweight E2 egocentric device is suited as a precursor to human demos. Under the scene pillar, this directly relates to the delivery risk of "HaMeR / MANO × smart home install…".

(Deep dive · 152-7) On HaMeR / MANO and wrist: the HaMeR lineage is sensitive to occlusion; ring + multi-channel redundancy reduces the proportion of invisible frames. Under the scene pillar, this directly relates to the delivery risk of "HaMeR / MANO × smart home install…".

(Deep dive · 152-8) On HaMeR / MANO and wrist: ActiveUMI demonstrates active perception; dual-channel acceptance of wrist + head-mounted is the procurement-grade answer. Under the scene pillar, this directly relates to the delivery risk of "HaMeR / MANO × smart home install…".

(Extension · 152-B1) 2026-09-13 review: laboratory matrix-style capture requires defining three-level primary keys — operator_id, session_id, shard_id — to avoid filename collisions. If your team tags=wrist, HaMeR / MANO, smart home installation, scene, we recommend adding this to your project risk register.

(Extended · 152-B2) 2026-09-13 retrospective: When comparing against public benchmarks, only borrow task definitions and metrics, not data licensing boundaries. If your team tags=wrist,HaMeR / MANO,smart home installation,scenario, it is recommended to record this in the project risk register.

(Extension · 152-B3) 2026-09-13 review: egocentric-to-robot transfer should have a dedicated coordinate system appendix: head, wrist, world, robot_base transformation chain. If your team tags=wrist, HaMeR / MANO, smart home installation, scene, we recommend adding this to your project risk register.

(Extension · 152-B4) 2026-09-13 review: if HEVC transcoding rewrites timestamps, the original_pts field must be preserved in metadata. If your team tags=wrist, HaMeR / MANO, smart home installation, scene, we recommend adding this to your project risk register.

(Extension · 152-B5) 2026-09-13 review: ring-based point completion is suitable for sparse geometric constraints and should not replace high-resolution hand pixel supervision. If your team tags=wrist, HaMeR / MANO, smart home installation, scene, we recommend adding this to your project risk register.

Frequently Asked Questions (FAQ)

Q: Does TOBI provide the HaMeR / MANO dataset? No. HaMeR / MANO is a public research/community resource; TOBI only discusses specification comparison and capture hardware capabilities.

Q: Can using only wrist reproduce all of the paper's results? No, it cannot be automatically guaranteed. The papers also involve task design, annotation toolchains, and training code; the hardware is responsible for making the timeline and sensor fields verifiable and acceptable.

Q: What does the demo animation demo-hero-e6.webp represent? An illustrative animation showing wrist live recording and worn form factor; not official HaMeR / MANO published content.

Q: What attachments should I prepare when requesting a quote? Recommended attachments: https://arxiv.org/abs/2312.06551, a target hours/scenario table, a Must-field checklist, and whether wrist/ring/matrix networking is required.

Next step: specification comparison and evaluation prototype

If you are planning wrist, HaMeR / MANO, smart home installation, scene scenarios against HaMeR / MANO, please contact TOBI with your Must-field checklist to apply for a wrist evaluation unit or a joint dataset delivery plan.

Read wrist product page, Developer Documentation · Device SDK, or Submit Quote Request and Technical Evaluation.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 1) When multiple capture operators work in parallel, mixing NTP and hardware time sources will prevent shards from being merged; a unified time source must be used. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 2) Health monitoring should include camera dropout, IMU saturation, remaining storage, and thermal throttling. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 3) Privacy: faces, house numbers, and screens require a redaction pipeline, and redaction logs must be auditable. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 4) Version ledger: firmware, calibration, APP, host scripts, DatasetServer — five version number categories bound to the session. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 5) The annotation toolchain is decoupled from the hardware; but exports must reference calib_version and sync_report. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 6) A VLA recipe should declare the language instruction alignment method: manual trigger vs. ASR timestamps. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 7) Human-to-robot transfer requires declaring the action space: joint vs. end-effector vs. bimanual. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 8) It is recommended that procurement contract attachments include links to public papers for task reference only, without implying data transfer. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 9) The algorithm team should document the observation–action causal window in the data card, including whether frames from multiple streams are retained for 120ms before contact and 200ms after contact. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 10) During procurement review, require the supplier to provide P50/P95 curves of sync jitter, not single-point marketing figures. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 11) In long-duration dex capture, thermal drift and bandwidth contention amplify soft alignment errors; hardware triggering is superior to pure software timestamping. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 12) Failed samples must include a timeline health score; otherwise, VLA will treat interpolated frames after repair as real contact. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 13) Cross-day capture requires declaring the time source switching strategy: whether CDC-ACM, PPS, or GNSS are mixed. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 14) Inconsistent versions of the wrist-mounted and head-mounted extrinsic calibration cause a systematic shift in MANO supervision. Run regression tests when the wearer changes. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 15) Semantic gestures can serve as weak supervision, rather than independent labels, only when the OpenXR gesture stream and video frames share the same time base. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 16) DatasetServer shard limits and disk flush strategy affect whether the "last frame" is lost. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 17) Matrix-style data capture in the lab should define a three-level primary key of operator_id, session_id, and shard_id to avoid filename collisions. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 18) When comparing against public benchmarks, only borrow the task definitions and metrics, not the data licensing boundaries. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 19) Ego-to-robot transfer should include a separate coordinate frame attachment: the transformation chain for head, wrist, world, and robot_base. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 20) If HEVC transcoding rewrites timestamps, the original_pts field must be preserved in the metadata. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 21) Ring-based point completion is suitable for sparse geometric constraints and should not replace high-resolution hand pixel supervision. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 22) If the device has on-board SLAM (e.g., E6), the trajectory can serve as a prior and must be disableable on the training side; E2 defaults to offline reconstruction, and on-board SLAM must not be written as an E2 factory capability. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 23) Collaborative Ego scenarios must declare the speech/instruction synchronization strategy to avoid audio-visual causal misalignment. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 24) QA spot checks should re-run the same script on a Linux host to ensure the delivery is auditable. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 25) Illumination variation in kitchen and home long-tail scenarios requires exposure strategy to be written into the SOP: fixed, manual, and adaptive modes must be consistent. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 26) When 60fps stereo capture is combined with a 30fps auxiliary stream, clearly specify the downsampling and phase rules. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 27) When aligning 200Hz IMU with video frames, it must be declared whether interpolation or nearest-neighbor is used, along with boundary frame handling. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 28) ORB-SLAM3-class VIO baselines emphasize multi-sensor timestamps; Ego devices should align to equivalent semantics. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 29) Open X-Embodiment emphasizes cross-platform action distributions; the Ego field schema should reserve an embodiment_id field. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 30) DROID-class robot data lacks human priors; E2's lightweight Ego is suitable as a pre-stage for human demonstration. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 31) The HaMeR lineage is sensitive to occlusion; ring + multi-path redundancy reduces the proportion of invisible frames. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 32) ActiveUMI demonstrates active perception; dual-channel acceptance of wrist-mounted plus head-mounted streams is the procurement-grade answer. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 33) World model training relies more on long-duration consistent timelines; random cropping of short clips destroys state continuity. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 34) Diffusion policies are sensitive to contact phase; the data card should annotate the start and end frames of contact_phase. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 35) The Sim2Real pipeline should not use different timestamp units in sim and real. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 36) Enterprise content funnel: paper page → spec page → prototype → small-batch data → scaled procurement, with exit criteria at each step. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 37) This article focuses on engineering acceptance field descriptions, so that procurement and algorithm teams can copy them directly into RFQ attachments. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 38) When linking to SDK documentation, fix the anchor to #device-sdk to reduce reader disorientation. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 39) The video poster matches the hero image, reducing first-screen CLS and trust cost. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 40) The FAQ must reiterate dataset boundaries to prevent sales from over-promising. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 41) There may be a gap between the E8 ten-channel and TOF channels in R&D integration versus mass-production specifications; the contract should specify the delivery level clearly. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 42) Motion-capture bridging is a Stretch capability and requires a separate milestone and acceptance script. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 43) Global shutter reduces geometric distortion in fast lateral motion scenarios compared to rolling shutter, benefiting stereo matching. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 44) The choice of 65mm-level baseline affects depth accuracy and wearing volume, and should be consistent across the product page and data card. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 45) fMP4 segments facilitate browser preview, but the training side requires a raw or lossless backup strategy. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 46) MCAP is well-suited to the ROS2 ecosystem; field naming should follow the team's schema registry. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 47) Scripts like linux_run_time_sync.sh should be versioned and cross-referenced with the firmware README. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 48) The open-source e2-sdk/e6-sdk only helps you get started; mass-production procurement still follows the commercial delivery package. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 49) When multiple capture operators work in parallel, mixing NTP and hardware time sources will prevent shards from being merged; a unified time source must be used. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 50) Health monitoring should include camera dropout, IMU saturation, remaining storage, and thermal throttling. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 51) Privacy: faces, house numbers, and screens require a redaction pipeline, and redaction logs must be auditable. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 52) Version ledger: firmware, calibration, APP, host scripts, DatasetServer — five version number categories bound to the session. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-152-scene-wrist-智能-s080 · 53) The annotation toolchain is decoupled from the hardware; but exports must reference calib_version and sync_report. When assessing wrist against HaMeR / MANO (2024), archive this together with the acceptance checklist dated 2026-09-13.