I'm an MSc student in Artificial Intelligence at ETH Zürich and the University of Zürich. My work lies at the intersection of computer vision, robotics, and language-grounded AI, aiming to give machines a richer understanding of the physical world, from indoor localization via natural language to whole-body imitation learning for humanoid robots.
- 🔭 Currently: Graduate Student Researcher at the ETH Computer Vision and Geometry Group, building HERMES SLAM (CVPR 2027 target) with Dr. Dániel Béla Baráth; also RL Engineer in the Humanoid Group of the ETH Robotics Club
- 🌱 Exploring: Embodied AI · Vision-Language Models · Sim-to-Real Transfer · 3D Scene Understanding
- 🤝 Open to collaborate on: Spatial reasoning, RL for robotics, multimodal perception
- 💬 Ask me about: SLAM, scene graphs, indoor localization, humanoid control
- 📫 Reach me at: rzendehdel@ethz.ch
- 🌍 Based in: Zürich, Switzerland 🇨🇭
- 🗣️ Speaks: English · Persian · German · Japanese
|
ETH D-INFK · Computer Vision and Geometry Group · Graduate Student Researcher (Mar 2026 – Present) A state-of-the-art Dynamic SLAM system developed at CVG with Dr. Dániel Béla Baráth, advancing real-time localization and mapping in scenes with moving objects, where classical SLAM assumptions break down.
|
|
|
ETH CVG Lab × UZH AI/ML Group The first pipeline for fine-grained indoor localization from natural language alone, without any camera input. A dual-branch GATv2 + CLIP architecture for scene retrieval (+8 pp Top-1 over SOTA), a visibility-based floor-grid scoring module that reaches ~1 m median error, and a Bayesian dialog module that drives median error down to 7 cm via targeted yes/no questions.
|
ETH Ecosystem & Landscape Evolution Lab A Transformer-based mask modeling framework (inspired by Pl@ntBERT) on phylogenetic embeddings to detect ecologically suitable but absent marine species, quantifying anthropogenic impact at scale. Also built an end-to-end FASTQ → DADA2 → GBIF pipeline in collaboration with marine ecologists.
|
|
ETH Robotics Club Implementing TWIST in NVIDIA IsaacLab to train a Unitree G1 locomotion policy on AMASS / MoCap data with robust sim-to-real transfer. Fine-tuning NVIDIA GR00T N1.6 on teleoperation data and deploying SONIC for real-time whole-body control, alongside a low-cost VR-based teleoperation rig built with PICO headsets.
|
ETH CVG Lab Onboard 3D perception for the Spot robot: dense RGB-D SLAM with TSDF volumetric fusion from a single monocular camera, plus a dynamic scene graph generator powered by OpenMask3D for open-vocabulary instance segmentation, letting the robot semantically understand and update its world during interaction.
|
|
Microsoft Spatial AI Lab A voice-based navigation assistant for smart glasses that guides users with context-aware, landmark-based verbal cues instead of metric instructions. Combines image-based localization, semantic landmark extraction, and mesh-aligned grounding inside Habitat-Sim, evaluated on a 3D mesh of the ETH HG building.
|
UZH Robotics & Perception Group A PPO-based vision policy for an autonomous "camera drone", trained in Flightmare / Agilicious to track dynamic targets while keeping safe flight dynamics. Deployed on real hardware through a 60 Hz ROS control loop, with extensive domain randomization for robust sim-to-real transfer.
|
"The best way to predict the future is to invent it."
Alan Kay