DynastGNN: Dynamic Spatio-Temporal Hierarchical Graph Neural Network for Visuotactile 6D Pose Estimation of an In-Hand Object
Snehal Dikhale, et al.
Paper in Progress, 2025
Snehal S. Dikhale
Robotics Researcher @ Honda Research Institute
5 yrs industryM.S. Robotics
The industry has mastered seeing. I want to give robots the ability to truly feel. That means cracking tactile representation and using it to unlock dexterous manipulation.
Right now I'm extending Vision-Language-Action architectures with touch, connecting foundation models all the way down to real hardware.
I'm equal parts researcher and engineer, and I genuinely love both. I call it hardware intuition. Always happy to connect, whether it's research, life, or just geeking out about robots.
Research & Practice
Researcher by Nature, Engineer by Practice
Simulation
High-fidelity physics modeling
Domain randomization
Sim-to-real transfer
Algorithm
Multimodal learning (Vision + Touch)
Graph neural networks
Representation learning
Hardware
Real-world deployment
Tactile sensor integration
Multi-fingered manipulation
Experience
Research Engineer II, Robotics
CurrentHonda Research Institute · Apr 2024 – Present
25%
tasksuccess
30%
poseconsistency
3
patentsfiled
- Architected a multimodal reasoning system by extending Vision-Language Model (VLM) backbones with custom tactile, force, and depth modality projection layers, achieving efficient failure reasoning significantly faster than state-of-the-art baselines
- Co-designed a multimodal self-attention action-conditioned model to generate context from vision, tactile, and proprioception, improving task success by 25%; mentored an intern through the full lifecycle of this module
- Designed and developed a spatio-temporal graph-based representation learning framework combining video, depth, proprioception, and taxel-level tactile data, improving pose estimation temporal consistency by 30% in dynamic environments
- Collaborated with cross-functional and international research teams to drive end-to-end project execution
- One of 30 individuals selected across all of Honda North America for leadership development training
VLMsMultimodal ReasoningSpatio-Temporal GNNsIntern Mentorship
Research Engineer I, Robotics
Honda Research Institute · Sep 2020 – Apr 2024
65%
sim-to-realgap
3×
tactileresolution
100+
robotexperiments
- Built an end-to-end perception pipeline for dexterous in-hand pose estimation under heavy occlusion, owning the full stack from algorithm design to deployment; validated robustness via 100+ real-robot experiments
- Solved the Sim-to-Real gap (closing it by 65%) by engineering a 220k-sample domain-randomized visuotactile dataset (RGB-D + tactile) in Unreal Engine
- Designed hardware-agnostic CNN-based and graph representations for vision, depth, and 3D tactile sensor fusion, reducing position error by ~35% and angular error by ~64% over vision-only baselines
- Contributed to contrastive learning techniques for taxel-based signals, achieving a 3× improvement in tactile resolution to enhance fine-grained manipulation capabilities
Sim-to-RealVisuotactile Sensing6D Pose EstimationContrastive Learning
Graduate Researcher
Worcester Polytechnic Institute · 2018 – 2020
78%
grasp success
3.8
GPA
4
projects
- M.S. Thesis: Built a simulation and benchmarking framework (Gazebo, MoveIt, Panda Arm, RealSense) to evaluate deep learning grasping algorithms; achieved 78% success with GQCNN and 65% with GPD on RGB-D data
- Human-Robot Handover: Designed interaction experiments using ROS/Python; trained ProMPs to predict Object Transfer Point (RMSE < 0.2m)
- Simulation of Control Techniques: Implemented Robust, PD, and PD+Gravity controllers for Baxter Arm; evaluated via MATLAB simulations
- Predicting Building Energy Consumption: Applied regression, random forest, and neural networks; achieved RMSE 1.27, ranked top 30% on Kaggle
- WIN Women's Young Investigator Fellowship – Awarded to the top 4 graduate female researchers in STEM at WPI
- Mentor, Women's Research and Mentorship Program – Mentored 1 undergraduate and 2 high school students; led robotics and 3D printing workshops
ROSGazeboMoveItDeep Learning for Grasping
Selected Patents & Publications
Vision-Language Models for Failure Reasoning in Multi-Fingered Dexterous Manipulation
S. Zhao*, S. Dikhale, et al.
* Mentored Intern
US Provisional Patent, 2025
Provisional PatentContext-Aware Multimodal Action Planning Using Tactile, Vision, and Language
A. Shahidzadeh*, S. Dikhale, et al.
* Mentored Intern
US Provisional Patent, 2025
Provisional Patent
Technical Skills
Research & AI
Embodied AIVision-Language Models (VLMs)Large Language Models (LLMs)Multimodal LearningDexterous ManipulationSim-to-Real Transfer3D Tactile RepresentationGraph Neural NetworksTransformersContrastive LearningComputer VisionDeep Learning
Software & Frameworks
PythonC++PyTorchHugging FaceCUDADockerGit
Simulation & Tools
ROS / ROS2MuJoCoIsaac SimUnreal EngineGazeboMoveItBlender
My Story
Medium
Robotics Chose Me, But I Choose It Every Day
A personal essay on what it really means to build a career in robotics — the doubt, the obsession, the hardware that breaks at 11pm, and why I'd choose it all over again.
Read on Medium