Publication visual-media audit
Publication visual-media audit
Base: master at 40ab5560713cce498d9eca85737b58e02eb2e00f
PR base refreshed to: master at ff290941999cb2a0c31b08e3599af2e6eac45172; the newer researcher biography is preserved.
Working branch: feature/publication-visual-previews
Audit scope: all 42 files in _publications/
Outcome
- Publication-card previews: 42 of 42 publications (9 suitable existing previews retained, 13 new video loops, 20 new paper-figure posters).
- Individual paper-page figures: 41 of 42 publications.
- New video loops: silent WebM/VP9 and MP4/H.264
yuv420p, with WebP posters and original aspect ratios. - Four existing static card images were replaced with associated video loops at the author’s request; all other suitable existing media was retained.
- Local website preview approved by the author on September 2, 2026; changes prepared for a reviewable PR targeting
master, without merging.
“Accessible PDF” means a full paper file was available for figure extraction during this audit; a publisher landing page by itself is not counted as accessible.
Per-publication audit
| Publication title | Existing media before this work | Available video | Accessible PDF | Recommended source | Publication-card preview | Card source | Individual paper-page main figure | Main-figure source | Files/source not accessible |
|---|---|---|---|---|---|---|---|---|---|
| Deep Reinforcement Learning Control of an Autonomous Wheeled Robot in a Challenge Task: Combined Visual and Dynamics Sensoring | None | None found | Yes — author-supplied PDF | Paper robot figure | wheeled-robot-challenge-main.webp |
Paper Fig. 1 | wheeled-robot-challenge-main.webp |
Paper Fig. 1, camera-equipped rover | — |
| Redundant Robot Kinematics Error Analysis for Neurosurgical Procedures | None | None found | Yes — author-supplied PDF | Paper robot/setup figure | neurosurgical-robot-arm-main.webp |
Paper Fig. 1 | neurosurgical-robot-arm-main.webp |
Paper Fig. 1, SEEG robot and guide | — |
| EEG-Based Epileptic Seizure Prediction Using Temporal Multi-Channel Transformers | None | None found | Yes | Paper architecture figure | eeg-seizure-transformer-main.webp |
Paper PDF | eeg-seizure-transformer-main.webp |
Paper model architecture | — |
| Electromyography-Based, Robust Hand Motion Classification Employing Temporal Multi-Channel Vision Transformers (BioRob 2022) | None | None found | Yes — author-supplied PDF | Paper interface photo for card; architecture for page | emg-hand-motion-interface.webp |
Paper Fig. 1 | emg-temporal-transformer-architecture-main.webp |
Paper transformer architecture | — |
| On EMG Based Dexterous Robotic Telemanipulation: Assessing Machine Learning Techniques, Feature Extraction Methods, and Shared Control Schemes | None | Author-associated video | Yes | Video for card; paper system figure for page | emg-telemanipulation.webm/.mp4/.webp |
Representative telemanipulation segment from AE2e8lkj55I |
emg-teleoperation-system-main.webp |
Paper system overview | — |
| Electromyography-Based, Robust Hand Motion Classification Employing Temporal Multi-Channel Vision Transformers (RA-L 2022) | None | None found | Yes — author-supplied PDF | Paper interface photo for card; architecture for page | emg-hand-motion-interface.webp |
Paper Fig. 1 | emg-temporal-transformer-architecture-main.webp |
Paper transformer architecture | — |
| Electromyography Based Decoding of Dexterous, In-Hand Manipulation Motions With Temporal Multichannel Vision Transformers | None | None found | Yes | Paper temporal-convolution/transformer diagram | emg-temporal-convolution-main.webp |
Paper PDF | emg-temporal-convolution-main.webp |
Paper model diagram | — |
| Comparing Human and Robot Performance in the Execution of Kitchen Tasks: Evaluating Grasping and Dexterous Manipulation Skills | None | Paper-associated video | Yes — author-supplied PDF | Video for card; paper experimental setup on page | human-robot-kitchen-tasks.webm/.mp4/.webp |
Representative robot kitchen-task segment from 7x-V8qCMQNI |
human-robot-kitchen-task-setup-main.webp |
Paper Fig. 2, kitchen-task data-collection setup | — |
| Lightmyography Based Decoding of Human Intention Using Temporal Multi-Channel Transformers | None | None found | Yes — author-supplied PDF | Paper armband for card; architecture for page | lightmyography-armband.webp |
Paper Fig. 1 | lightmyography-transformer-architecture-main.webp |
Paper TMC-ViT architecture | — |
| An Affordances and Electromyography Based Telemanipulation Framework for Control of Robotic Arm-Hand Systems | None | Paper-associated video | Yes — author-supplied PDF | Video for card; paper system framework on page | affordance-telemanipulation.webm/.mp4/.webp |
Representative arm-hand telemanipulation segment from PPgCIdII8Ao |
affordance-telemanipulation-framework-main.webp |
Paper Fig. 3, real-time telemanipulation framework | — |
| An Adaptive, Humanlike Prosthetic Hand Equipped with a Series Elastic Differential and a Lightmyography Based Control Interface | None | Paper-associated video | Yes — author-supplied PDF | Video for card; paper system setup on page | adaptive-prosthetic-hand.webm/.mp4/.webp |
Representative prosthetic-hand actuation segment from p0xvQdAkXa8 |
adaptive-prosthetic-hand-system-main.webp |
Paper Fig. 1, prosthetic hand and LMG interface | — |
| Multi-Grasp Classification for the Control of Robot Hands Employing Transformers and Lightmyography Signals | None | Paper-associated video | Yes — author-supplied PDF | Video for card; paper model architecture on page | lightmyography-multigrasp.webm/.mp4/.webp |
Representative multigrasp demonstration from QJ4IKUr4QEY |
lightmyography-multigrasp-transformer-main.webp |
Paper Fig. 4, TMC-ViT architecture | — |
| On Human Grasping and Manipulation in Kitchens: Automated Annotation, Insights, and Metrics for Effective Data Collection | None | None suitable found | Yes — author-supplied PDF | Paper setup for card; annotation pipeline for page | kitchen-grasping-data-collection.webp |
Paper Fig. 1 | kitchen-grasp-annotation-pipeline-main.webp |
Paper automated annotation pipeline | — |
| Employing Multi-Layer, Sensorised Kirigami Grippers for Single-Grasp Based Identification of Objects and Force Exertion Estimation | None | Paper-associated video | Yes — author-supplied PDF | Video for card; paper gripper design on page | kirigami-object-identification.webm/.mp4/.webp |
Representative sensorized-gripper experiment from 06G9P70_25Q |
kirigami-gripper-design-main.webp |
Paper Fig. 2, labeled kirigami pouch geometry | — |
| Scalable. Intuitive Human to Robot Skill Transfer with Wearable Human Machine Interfaces: On Complex, Dexterous Tasks | None | None suitable found | Yes — author-supplied PDF | Paper interface photo for card; workflow for page | wearable-skill-transfer.webp |
Paper Fig. 1 | human-robot-skill-transfer-workflow-main.webp |
Paper task-recording/replication workflow | — |
| On lightmyography based muscle-machine interfaces for the efficient decoding of human gestures and forces | lmg-armband-detail.jpg (preserved) |
None suitable found | Yes | Preserve card; use paper principle diagram on page | Existing lmg-armband-detail.jpg |
Existing repository project image | lightmyography-principle-main.webp |
Paper lightmyography principle figure | — |
| On Semi-Autonomous Robotic Telemanipulation Employing Electromyography Based Motion Decoding and Potential Fields | None | Paper-associated video | Yes — author-supplied PDF | Video for card; paper system framework on page | potential-fields-telemanipulation.webm/.mp4/.webp |
Representative potential-fields telemanipulation segment from CQFOD33NkEQ |
emg-potential-fields-framework-main.webp |
Paper Fig. 4, EMG/potential-fields framework | — |
| A Video Dataset of Everyday Life Grasps for the Training of Shared Control Operation Models for Myoelectric Prosthetic Hands | None | Project dataset link exists; no suitable downloadable preview found | Yes — author-supplied PDF | Paper prosthetic/camera figure | prosthetic-grasp-video-dataset-main.webp |
Paper Fig. 1 | prosthetic-grasp-video-dataset-main.webp |
Paper prosthetic device and camera views | — |
| Improving Failure Prediction in Aircraft Fastener Assembly Using Synthetic Data in Imbalanced Datasets | None | None found | Yes | Paper pipeline figure | grasp-feasibility-pipeline-main.webp |
Paper PDF | grasp-feasibility-pipeline-main.webp |
Paper pipeline | — |
| On Semi-Autonomous, Intuitive, Lightmyography Based Control of Humanlike Robotic and Prosthetic Hands Utilizing Video and IMU Data | None | None suitable found | Yes — author-supplied PDF | Paper user/setup image for card; control framework for page | semi-autonomous-prosthetic-control.webp |
Paper Fig. 1 | semi-autonomous-lmg-control-main.webp |
Paper semi-autonomous framework | — |
| On the Impact of Different Light Wavelengths in Decoding Human Intention in Lightmyography Controlled Prosthetic Hands | None | None found | Yes — author-supplied PDF | Paper sensor-placement figure | lmg-wavelength-comparison-main.webp |
Paper experimental setup | lmg-wavelength-comparison-main.webp |
Paper LMG channel placement | — |
| Electromyography Based Gesture Decoding Employing Few-Shot Learning, Transfer Learning, and Training From Scratch | None | None suitable found | Yes | Paper model architecture | few-shot-seizure-architecture-main.webp |
Paper PDF | few-shot-seizure-architecture-main.webp |
Paper architecture | — |
| Offline Versus Real-Time Grasp Prediction Employing a Wearable High-Density Lightmyography Armband: On the Control of Prosthetic Hands | offline-vs-realtime-grasp-prediction.webp (preserved) |
None suitable found | Yes | Preserve card; use paper hardware overview on page | Existing offline-vs-realtime-grasp-prediction.webp |
Existing repository poster | high-density-lightmyography-hardware-main.webp |
Paper armband/hardware figure | — |
| MIHRaGe: A Mixed-Reality Interface for Human-Robot Interaction via Gaze-Oriented Control | None | Paper-associated video | Yes | Video for card; paper interface diagram for page | mixed-reality-gaze-control.webm/.mp4/.webp |
Representative gaze-control interaction from K16a8Ve_x20 |
mixed-reality-gaze-system-main.webp |
Paper system/interface overview | — |
| Multi-Layer, Sensorized Kirigami Grippers for Delicate Yet Robust Robot Grasping and Single-Grasp Object Identification | None | No additional suitable video needed | Yes | Paper hardware/actuation figure | kirigami-finger-actuation-main.webp |
Paper PDF | kirigami-finger-actuation-main.webp |
Paper gripper actuation figure | — |
| A Vision-Based Shared-Control Teleoperation Scheme for Controlling the Robotic Arm of a Four-Legged Robot | spot-teleoperation.jpg |
Author-associated video | Yes | Video for card; paper assistance pipeline on page | vision-based-shared-control-teleoperation.webm/.mp4/.webp |
Representative robot-arm teleoperation segment from klgpq57c8UM |
autonomous-assistance-pipeline-main.webp |
Paper shared-control pipeline | — |
| The impact of feature scaling in machine learning: Effects on regression and classification tasks | feature-scaling.webp (preserved) |
None relevant | Yes | Preserve card; paper experiment overview on page | Existing feature-scaling.webp |
Existing repository poster | feature-scaling-experiment-main.webp |
Paper experiment overview | — |
| Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach | Existing uav-confined-spaces loop (preserved) |
Existing project animation | Yes | Preserve animation; paper system overview on page | Existing uav-confined-spaces.webm/.mp4/.webp |
Existing repository loop | uav-navigation-system-main.webp |
Paper navigation system figure | — |
| A Synthetic Dataset for Manometry Recognition in Robotic Applications | None | None suitable found | Yes | Paper multimodal pipeline | multimodal-teleoperation-pipeline-main.webp |
Paper PDF | multimodal-teleoperation-pipeline-main.webp |
Paper pipeline | — |
| Optimizing Grasping in Legged Robots: A Deep Learning Approach to Loco-Manipulation | None | Author-associated video | Yes | Video for card; paper grasp-model diagram for page | legged-robot-valve-grasping.webm/.mp4/.webp |
Representative robot valve-grasping segment from 7nv4rO5DJLM |
loco-manipulation-grasp-model-main.webp |
Paper model/system diagram | — |
| Combining Augmented Reality with Semi-autonomous, Lightmyography Based Control to Improve Usability of Prostheses | augmented-reality-prosthesis.webp (preserved) |
None suitable found | Yes | Preserve card; paper system overview on page | Existing augmented-reality-prosthesis.webp |
Existing repository poster | ar-shared-control-system-main.webp |
Paper AR/shared-control overview | — |
| Descriptor: Parasitoid Wasps and Associated Hymenoptera Dataset (DAPWH) | parasitoid-wasp-dataset.webp (preserved) |
None relevant | Yes | Preserve card; paper dataset structure on page | Existing parasitoid-wasp-dataset.webp |
Existing repository poster | parasitoid-wasp-dataset-structure-main.webp |
Paper dataset structure figure | — |
| Automated identification of Ichneumonoidea wasps via YOLO-based deep learning: Integrating HiresCam for Explainable AI | None | None relevant | Yes | Paper framework figure | wasp-identification-framework-main.webp |
Paper PDF | wasp-identification-framework-main.webp |
Paper operational framework | — |
| VLN on the Fly: A Fully Onboard Vision-Language Navigation Stack for Aerial Robots | Existing vln-on-the-fly loop (preserved) |
Project video | Yes | Preserve loop; project/paper system diagram on page | Existing vln-on-the-fly.webm/.mp4/.webp |
Existing repository loop | vln-on-the-fly-main.webp |
Genuine project system diagram | — |
| Biological Sex Determination in Cadavers Using Deep Learning Algorithms from Computed Tomography Images of Pelvis and Skull | None | None relevant | Yes | Paper pipeline figure | cadaver-sex-determination-pipeline-main.webp |
Paper PDF | cadaver-sex-determination-pipeline-main.webp |
Paper pipeline | — |
| Evaluating Zero-Shot and One-Shot Adaptation of Small Language Models in Leader-Follower Interaction | None | None suitable found | Yes | Paper dataset/evaluation pipeline | leader-follower-dataset-pipeline-main.webp |
Paper PDF | leader-follower-dataset-pipeline-main.webp |
Paper pipeline | — |
| A Leaf-Level Dataset for Soybean-Cotton Detection and Segmentation | soybean-cotton-leaf-dataset.webp (preserved) |
None relevant | Yes | Preserve card; paper annotation overview on page | Existing soybean-cotton-leaf-dataset.webp |
Existing repository poster | leaf-dataset-annotation-main.webp |
Paper annotation figure | — |
| MIRA: A Modular Open-Source Micro-UAV for Indoor Research | uav-functional-layers-main.webp |
Associated indoor-flight video | Yes | Video for card; paper functional-layers diagram on page | mira-indoor-flight.webm/.mp4/.webp |
Representative indoor UAV flight segment from Om3usIreKDk |
uav-functional-layers-main.webp |
Paper architecture diagram | — |
| Towards Capability-Aware Traversability Navigation for Unstructured Environments | Existing capability-aware-traversability loop (preserved) |
Project/paper video | Yes | Preserve loop; paper system overview on page | Existing capability-aware-traversability.webm/.mp4/.webp |
Existing repository loop | traversability-navigation-system-main.webp |
Paper capability-aware navigation overview | — |
| Mind the Phase: Effective Rank and Representation Health in Legged Locomotion | Existing mind-the-phase loop (preserved) |
Paper-associated video | No — linked site PDF returns 404 | Preserve existing animation; omit individual-page main figure as approved by the author | Existing mind-the-phase.webm/.mp4/.webp |
Existing repository loop | None (author-approved exception) | — | https://www.ricardovgodoy.com/files/2026_corl.pdf returns 404; not a blocker for this PR |
| Language-Guided Grasping under Partial Observation for Mobile Manipulation in Field Inspection and Maintenance | language-guided-grasping.jpg |
Project/paper video | Yes | Video for card; paper system overview on page | language-guided-grasping.webm/.mp4/.webp |
Representative robot grasp-planning/execution segment from 9Ca3zzUI8Ic |
language-guided-grasping-system-main.webp |
Paper system diagram | — |
| From Perception to Assistance: Open-Vocabulary Shared Autonomy for Robotic Manipulation | shared-autonomy-hero.jpg |
Project/paper video | Yes | Video for card; paper shared-autonomy diagram on page | open-vocabulary-shared-autonomy.webm/.mp4/.webp |
Representative valve-manipulation segment from UNAeSZh0kCU |
shared-autonomy-potential-fields-main.webp |
Paper potential-fields/shared-autonomy figure | — |
Blocked source summary
All 42 publication cards now have a genuine publication, paper, project, or associated-video preview.
The author explicitly approved leaving 2026-rank (“Mind the Phase”) without an individual-page main figure. Its existing animated preview remains available wherever referenced. No additional source is required for this PR.
Validation summary
- YAML/front matter: valid for all 42 publications.
- Referenced media paths: all present.
- Image decoding: all posters and main figures readable.
- Video codecs: every WebM is VP9; every MP4 is H.264 with
yuv420p. - New loops: six seconds, muted, representative non-title segments.
- Main figures: original aspect ratio retained; no fixed-height crop or
object-fit: cover. - Responsive preview: no horizontal overflow at 1440×900 or 390×844; wide and tall figures remain uncropped and precede the Abstract.
- Complete Jekyll build: successful. Remaining build warnings are pre-existing legacy layout/Sass warnings.
Homepage and Research media
The homepage now has seven silent looping previews (four selected publications and three selected projects). Research has seven (two overview visuals and five project previews). Existing video assets are reused without re-encoding, and all displayed frames use containment rather than cropping. The profile portrait remains unchanged.
| Project/research theme | Locations | Preview | Source and relationship |
|---|---|---|---|
| Open-vocabulary shared autonomy | Homepage publication and project; Research project | open-vocabulary-shared-autonomy.webm/.mp4/.webp |
Associated paper video, exact match |
| Language-guided grasping | Homepage project; Research project and robot-autonomy overview | language-guided-grasping.webm/.mp4/.webp |
Associated paper video, exact match and representative autonomy example |
| Capability-aware navigation | Homepage publication and project; Research project | Existing capability-aware-traversability.webm/.mp4/.webp |
Existing suitable project preview retained |
| Vision-based Spot teleoperation | Homepage publication; Research project and human-robot-interaction overview | vision-based-shared-control-teleoperation.webm/.mp4/.webp |
Associated paper video, exact match and representative interface example |
| Wearable intent decoding / LMG | Homepage LMG item; Research wearable project | lightmyography-multigrasp.webm/.mp4/.webp |
EMBC 2023 multigrasp demonstration, related work explicitly labeled and linked to its source publication |
The related LMG video is a homepage-only override for the Scientific Reports paper; its own publication-card image and individual-page main figure remain unchanged. The Research wearable project is a broader research theme and also identifies the related video’s source.