Back to News & Insights
Frontier Observations

Contact conditions: a DROID-inspired E6 data slicing strategy

Drawing on DROID's task structure, discuss how E6 capture clips can serve contact conditioning: contact windows, failure retention, and how action-semantic fields are written on the model side. Aimed at teams planning

2026-09-08
Chief News Officer, TOBI Technology
Frontier Observations
contact condition: DROID-inspired E6 data slicing strategy (212)
Chief Insights Research Frontiers 2026-09-13 Chinese original: about 5031 characters

Market & Solutions Perspective | 2026-09-13

Around 2026-09-13, the question customers ask most often is not "does the paper exist" but "can we accept the device and data according to DROID's criteria". The public claim is: a distributed robot teleoperation dataset emphasizing real-world scene diversity and control alignment. TOBI's role is to write E6 as deliverable fields in the quote request list, not to imply exclusive data assets.

Drawing on DROID's task structure, discuss how E6 capture clips serve contact conditioning: the model-side handling of contact windows, failure retention, and action semantic fields. For teams planning Ego datasets, VLA training, and robot transfer around 2026, emphasize auditable delivery, versioned calibration, and hardware-synchronized quality checks, and avoid misreading public benchmarks as any single vendor's exclusive capability.

Live demo demo-wrist
Live demo animation (demo-wrist.webp): shows the E6 recording pipeline for comparison against DROID's public specifications; not official DROID material.

What the Paper Timeline Tells Us

Around 2024, DROID pushed the community discussion toward a clear question: the distributed robot teleoperation dataset emphasizes real-world scene diversity and control alignment. 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 DROID 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 model-type tasks (this article's slug: news-seo-212-model-e6-m140), the paper timeline also indicates when "failure cases and long-tail scenarios" are incorporated into the benchmark protocol. Constraints that appear late often have more impact on VLA training than early-stage scale figures; equipment selection should reserve the ability to retain time windows before and after contact.

Dataset Boundary Statement

DROID and its link https://arxiv.org/abs/2403.12945 in this article are in a public research context; TOBI does not claim ownership, hosting, or exclusive distribution of this dataset.

contact condition: DROID-inspired E6 data slicing strategy (212)
Figure 1 | Contact conditioning: DROID-inspired E6 data slicing … corresponds to the E6 live unit and wearing reference (not official DROID material).

Acceptable requirements for capture hardware

Translating DROID's one-line claim into procurement language starts with defining "acceptable fields" rather than restating that the distributed robot teleoperation dataset emphasizes real-world scene diversity and control alignment. 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 the SOP (2026-09-13 edition), bound to the E6 evaluation prototype:

  1. Freeze the E6 firmware and SDK versions, and reproduce the minimal script set for the DROID comparison experiment.
  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 segments for multi-view consistency across the E6, DROID, contact conditioning, model tag scenarios.
  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.
contact condition: DROID-inspired E6 data slicing strategy (212)
Figure 2 | Multi-view/scenario diagram for comparing DROID's task density and visibility assumptions.

Mapping to TOBI E6 Product Capabilities

TOBI E6 is a six-channel camera production-grade capture platform with on-board SLAM and OpenXR gesture pipeline integration. Host-side CDC-ACM time synchronization, DatasetServer sharding, and health monitoring form a standard delivery loop; suitable for dexterity, collaborative Ego, and multimodal long-horizon tasks.

In comparison with DROID: a distributed robot teleoperation dataset emphasizing real-world scene diversity and control alignment. On the device side, this should be translated into clickable product fields — for example frame rate/exposure/IMU frequency, whether on-device SLAM serves as a trajectory prior, and whether gesture/ring/wrist are time-synchronized in the same domain. Readers should go to /product-e6.html and /docs.html#device-sdk to verify the README and delivery package, rather than assuming that the paper configuration equals the factory default.

When pillar=model and E6 is the primary offering, it is recommended to split "paper metrics" into Must (without which we will not purchase) and Stretch (co-development with R&D). Must typically covers hard synchronization, calibration version, and recording container time semantics; Stretch may cover motion-capture bridging, ten-channel expansion, or cross-laboratory matrixization.

  • E2 positioning: binocular global shutter, offline-reconstruction-friendly, lightweight human-demonstration front-end (can still serve as a secondary network node when this article primarily recommends E6).
  • 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.
contact condition: DROID-inspired E6 data slicing strategy (212)
Figure 3 | E6 appearance as shown on the product page, for readers to jump to /product-e6.html to verify specifications.

Engineering deep dive: turning paper metrics into gates by scenario

(Deep Dive · 212-1) For DROID and E6: lighting variation in kitchen/home long-tail scenarios requires the exposure strategy to be written into the SOP — fixed/manual/adaptive must be consistent. Under the model pillar, this directly relates to the delivery risk of "Contact conditioning: DROID-inspired …".

(Deep dive · 212-2) For DROID and E6: if 60fps stereo is mixed with the 30fps side path, downsampling and phase rules must be clearly specified. Under the model pillar, this directly relates to the delivery risk of "contact conditions: DROID-inspired…".

(Deep Dive · 212-3) For DROID and E6: when aligning the 200 Hz IMU with video frames, state whether interpolation or nearest-neighbor is used, and how boundary frames are handled. Under the model pillar, this directly relates to the delivery risk of "Contact conditioning: DROID-inspired …".

(Deep Dive · 212-4) For DROID and E6: ORB-SLAM3-style VIO baselines emphasize multi-sensor timestamps; ego devices should align to equivalent semantics. Under the model pillar, this directly relates to the delivery risk of "Contact conditions: DROID-inspired …".

(Deep Dive 212-5) On DROID and E6: Open X-Embodiment emphasizes cross-embodiment action distributions; the Ego field schema should reserve an embodiment_id. Under the model pillar, this directly relates to the delivery risk of "contact conditions: DROID-inspired...".

(Deep Dive 212-6) On DROID and E6: DROID-style robot data lacks human priors; the lightweight E2 Ego is suitable as a pre-station for human demonstrations. Under the model pillar, this directly relates to the delivery risk of "contact conditions: DROID-inspired...".

(Deep Dive 212-7) On DROID and E6: the HaMeR lineage is sensitive to occlusion; rings plus multi-channel redundancy reduce the proportion of invisible frames. Under the model pillar, this directly relates to the delivery risk of "contact conditions: DROID-inspired...".

(Deep Dive 212-8) On DROID and E6: ActiveUMI demonstrates active perception; dual-channel acceptance of wrist-mounted and head-mounted streams is a procurement-grade answer. Under the model pillar, this directly relates to the delivery risk of "contact conditions: DROID-inspired...".

(Extension 212-B1) 2026-09-13 retrospective: matrixed laboratory capture must define three-level primary keys — operator_id, session_id, shard_id — to avoid filename collisions. If your team's tags are E6, DROID, contact conditions, model, we recommend recording this in the project risk register.

(Extended · 212-B2) 2026-09-13 retrospective: When comparing against public benchmarks, borrow only the task definitions and metrics, not the data licensing boundaries. If your team tags=E6,DROID,contact conditions,model, it is recommended to record this in the project risk register.

(Extension 212-B3) 2026-09-13 retrospective: Ego-to-robot transfer should include a separate coordinate-frame appendix covering the head, wrist, world, and robot_base transform chains. If your team's tags are E6, DROID, contact conditions, model, we recommend recording this in the project risk register.

(Extension 212-B4) 2026-09-13 retrospective: if HEVC transcoding rewrites timestamps, the original_pts field must be preserved in metadata. If your team's tags are E6, DROID, contact conditions, model, we recommend recording this in the project risk register.

(Extension · 212-B5) 2026-09-13 retrospective: ring-based point supplementation suits sparse geometric constraints and should not replace high-resolution hand pixel supervision. If your team tags=E6, DROID, contact conditions, model, it is recommended to write this into the project risk register.

Frequently Asked Questions (FAQ)

Q: Does TOBI provide the DROID dataset? Not provided. DROID is a public research/community resource; TOBI only discusses specification comparison and capture hardware capabilities.

Q: Can E6 alone reproduce all the results in the paper? 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-wrist.webp represent? An illustrative animated image showing E6 real-device recording and wearing configuration; not official DROID release material.

Q: What attachments should I prepare when requesting a quote? Recommended attachments: https://arxiv.org/abs/2403.12945, 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 an E6, DROID, contact conditions, model scenario with reference to DROID, please contact TOBI with your Must-field checklist to apply for an E6 evaluation unit or a joint dataset delivery plan.

Read E6 Product Page, Developer Documentation · Device SDK, or Submit Quote Request and Technical Evaluation.

(Appendix · news-seo-212-model-e6-m140 · 1) This article focuses on engineering acceptance field descriptions, so that procurement and algorithm teams can copy them directly into RFQ attachments. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 2) When linking to SDK documentation, fix the anchor to #device-sdk to reduce reader disorientation. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 3) The video poster matches the hero image, reducing first-screen CLS and trust cost. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 4) The FAQ must reiterate dataset boundaries to prevent sales from over-promising. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 5) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 6) Motion-capture bridging is a Stretch capability and requires a separate milestone and acceptance script. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 7) Global shutter reduces geometric distortion in fast lateral motion scenarios compared to rolling shutter, benefiting stereo matching. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 8) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 9) fMP4 segments facilitate browser preview, but the training side requires a raw or lossless backup strategy. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 10) MCAP is well-suited to the ROS2 ecosystem; field naming should follow the team's schema registry. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 11) Scripts like linux_run_time_sync.sh should be versioned and cross-referenced with the firmware README. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 12) The open-source e2-sdk/e6-sdk only helps you get started; mass-production procurement still follows the commercial delivery package. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 13) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 14) Health monitoring should include camera dropout, IMU saturation, remaining storage, and thermal throttling. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 15) Privacy: faces, house numbers, and screens require a redaction pipeline, and redaction logs must be auditable. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 16) Version ledger: firmware, calibration, APP, host scripts, DatasetServer — five version number categories bound to the session. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 17) The annotation toolchain is decoupled from the hardware; but exports must reference calib_version and sync_report. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 18) A VLA recipe should declare the language instruction alignment method: manual trigger vs. ASR timestamps. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 19) Human-to-robot transfer requires declaring the action space: joint vs. end-effector vs. bimanual. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 20) It is recommended that procurement contract attachments include links to public papers for task reference only, without implying data transfer. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 21) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 22) During procurement review, require the supplier to provide P50/P95 curves of sync jitter, not single-point marketing figures. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 23) In long-duration dex capture, thermal drift and bandwidth contention amplify soft alignment errors; hardware triggering is superior to pure software timestamping. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 24) Failed samples must include a timeline health score; otherwise, VLA will treat interpolated frames after repair as real contact. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 25) Cross-day capture requires declaring the time source switching strategy: whether CDC-ACM, PPS, or GNSS are mixed. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 26) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 27) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 28) DatasetServer shard limits and disk flush strategy affect whether the "last frame" is lost. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 29) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 30) When comparing against public benchmarks, only borrow the task definitions and metrics, not the data licensing boundaries. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 31) Ego-to-robot transfer should include a separate coordinate frame attachment: the transformation chain for head, wrist, world, and robot_base. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 32) If HEVC transcoding rewrites timestamps, the original_pts field must be preserved in the metadata. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 33) Ring-based point completion is suitable for sparse geometric constraints and should not replace high-resolution hand pixel supervision. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 34) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 35) Collaborative Ego scenarios must declare the speech/instruction synchronization strategy to avoid audio-visual causal misalignment. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 36) QA spot checks should re-run the same script on a Linux host to ensure the delivery is auditable. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 37) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 38) When 60fps stereo capture is combined with a 30fps auxiliary stream, clearly specify the downsampling and phase rules. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 39) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 40) ORB-SLAM3-class VIO baselines emphasize multi-sensor timestamps; Ego devices should align to equivalent semantics. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 41) Open X-Embodiment emphasizes cross-platform action distributions; the Ego field schema should reserve an embodiment_id field. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 42) DROID-class robot data lacks human priors; E2's lightweight Ego is suitable as a pre-stage for human demonstration. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 43) The HaMeR lineage is sensitive to occlusion; ring + multi-path redundancy reduces the proportion of invisible frames. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 44) ActiveUMI demonstrates active perception; dual-channel acceptance of wrist-mounted plus head-mounted streams is the procurement-grade answer. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 45) World model training relies more on long-duration consistent timelines; random cropping of short clips destroys state continuity. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 46) Diffusion policies are sensitive to contact phase; the data card should annotate the start and end frames of contact_phase. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 47) The Sim2Real pipeline should not use different timestamp units in sim and real. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 48) Enterprise content funnel: paper page → spec page → prototype → small-batch data → scaled procurement, with exit criteria at each step. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 49) This article focuses on engineering acceptance field descriptions, so that procurement and algorithm teams can copy them directly into RFQ attachments. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 50) When linking to SDK documentation, fix the anchor to #device-sdk to reduce reader disorientation. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 51) The video poster matches the hero image, reducing first-screen CLS and trust cost. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 52) The FAQ must reiterate dataset boundaries to prevent sales from over-promising. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 53) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 54) Motion-capture bridging is a Stretch capability and requires a separate milestone and acceptance script. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 55) Global shutter reduces geometric distortion in fast lateral motion scenarios compared to rolling shutter, benefiting stereo matching. When assessing E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.

(Appendix · news-seo-212-model-e6-m140 · 56) 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 E6 against DROID (2024), archive this together with the acceptance checklist dated 2026-09-13.