CV PDF
simkaned@gmail.com ·
s.nedelchev@innopolis.university
simeon-ned.github.io ·
Presentation ·
github.com/simeon-ned ·
X ·
Google Scholar
Professional Experience
Developing learning-based whole-body control, data-driven motion generation, and estimation methods for humanoid and articulated robots. Building simulation pipelines, motion libraries, and deployable control stacks with academic and industry partners.
Developed the RL whole-body control and locomotion policies demonstrated on the Green humanoid at AIJ Conference 2025. Focused on control, with modeling, MuJoCo simulation, and training/evaluation pipelines; also performed motor and actuator system identification (video).
Teaching advanced courses in robotics, mathematical modeling, motion planning, and applied and nonlinear control. Curriculum development and student mentoring in dynamics, simulation, and embodied AI.
Mathematical modeling, identification, and control of twisted-string actuators; optimal nonlinear control and trajectory optimization; mechanical and electrical prototyping of novel robotic systems.
Analysis, prototyping, and nonlinear control of twisted-string actuators; hardware implementation of advanced control algorithms.
Education
Thesis: Dynamic parameter estimation and adaptive control over robotic systems: generalized momentum approach.
Thesis: Development and research of a dynamic model of a robot manipulator.
Selected Research & Software Projects
WBC-Gen: Reactive Generative Motion Planner — fast proprio-conditioned latent flow-matching planner that emits trackable WBC references for a frozen whole-body controller; generalizable across tasks under one unified WBC contract; can recover and stand up from failed states without a fall/stand mode FSM. Gen and WBC run together on the Unitree G1 onboard CPU, with walk / sprint teleop, disturbance rejection, and agile recovery on hardware. Try Gen alongside WBC tracking (WASD to steer, Shift to sprint; G switches clips ↔ Gen); deploy code in wbc-g1-deploy; training code and paper coming soon.
WBC-Mjlab: Whole-Body Control in MuJoCo Lab (project page; web demo) — shared MDP for whole-body motion tracking in mjlab: multi-clip training, paper-specific task presets (ZEST, BeyondMimic-style RSI, and related setups), motion-data pipeline, and sim-to-real export for humanoids.
PSM: Predictive Style Matching for Natural Locomotion (project page) — offline predictor maps lower-body state and velocity commands to upper-body and gait targets during RL training; deployed on the Unitree G1 with task-only inference at runtime. arXiv:2606.07083 (2026).
Locomotion and Whole-Body Control for Sber Green (AIJ 2025 presentation) — developed the RL locomotion and whole-body control policies demonstrated on the Green humanoid at AIJ 2025, improving gait naturalness; RL whole-body control trained on synthetically generated reference trajectories (without mocap capture or retargeting) with unified tracking for teleoperation, dance, and zero-shot skills.
Open Source Contributions
Pinocchio — contributor to the rigid-body dynamics library (inertia parametrizations and physical consistency).
Pink — contributor to differential inverse kinematics for Pinocchio (tasks, constraints, and examples).
Mink
— contributed EqualityConstraintTask for closed-chain mechanisms; humanoid and manipulation examples in
the MuJoCo port of Pink.
GMR: General Motion Retargeting — contributor (SOMA BVH format and multi-robot configs).
mujoco-sysid — contributor; system identification in MuJoCo and MJX (parameter estimation, dynamics regressors).
MJINX: Differentiable GPU-accelerated Numerical IK — co-author (JAX and MuJoCo MJX).
Publications
- Nedelchev S, Chaikovskaia E, Davydenko E, Zaliaev E, Gorbachev R. Predictive Style Matching: Natural and Robust Humanoid Locomotion. arXiv:2606.07083, 2026. [Paper]
- Maslennikov E, Zaliaev E, Dudorov N, Shamanin O, Karanov D, Afanasev G, Burkov A, Lygin E, Nedelchev S, Ponomarev E. Robust RL Control for Bipedal Locomotion with Closed Kinematic Chains. arXiv:2507.10164, 2025. [Paper]
- Alentev I, Kozlov L, Domrachev I, Nedelchev S, Ryu JH. VIMPPI: Enhancing Model Predictive Path Integral Control with Variational Integration for Underactuated Systems. arXiv:2505.05507, 2025. [Paper]
- Nedelchev S, Kozlov L, Khusainov R, Gaponov I. Enhanced Adaptive Control over Robotic Systems via Generalized Momentum Dynamic Extensions. Russian Journal of Nonlinear Dynamics, 2023. [Paper]
- Fam CA, Nedelchev S. Optimization Driven Robust Control of Mechanical Systems with Parametric Uncertainties. Russian Journal of Nonlinear Dynamics, 2023. [Paper]
- Skvortsova V, Nedelchev S, Brown J, Farkhatdinov I, Gaponov I. Design, characterisation and validation of a haptic interface based on twisted string actuation. Frontiers in Robotics and AI, 2022.
- Nedelchev S, Skvortsova V, Guryev B, Gaponov I, Ryu JH. On Energy-Preserving Motion in Twisted String Actuators. IEEE Robotics and Automation Letters, 2021.
- Nedelchev S, Gaponov I, Ryu JH. Accurate dynamic modeling of twisted string actuators accounting for string compliance and friction. IEEE Robotics and Automation Letters, 2020.
- Jnadi A, Khusainov R, Nedelchev S, Savin S. Explicit Model Predictive Control Design based on Constrained Zonotope Propagation. DCNA, 2023. [Paper]
- Nedelchev S, Kirsanov D, Gaponov I, Seong H, Ryu JH. On Smooth Time-Optimal Trajectory Planning in Twisted String Actuators. ICRA, 2021. [Paper]
- Sabirova A, Nedelchev S, Gaponov I. Parameter Identification in Mechanical Systems with Energy-Based Regressor: Preliminary Study. NIR, 2021.
- Nedelchev S, Kirsanov D, Gaponov I. IMU-based Parameter Identification and Position Estimation in Twisted String Actuators. IROS, 2020.
- Balakhnov O, Nedelchev S, Gaponov I. Preliminary Study on Slack-Free Model Predictive Control of Twisted String-Based Antagonistic Joints. NIR, 2020.
- Nedelchev S, Gaponov I, Ryu JH. High-bandwidth control of twisted string actuators. ICRA, 2019.
- Nedelchev S, Gaponov I, Ryu JH. Design of robotic gripper with constant transmission ratio based on twisted string actuator. IROS, 2018.
- Kosterev D, Vorotnikov A, Nedelchev S, Romash E, Poduraev Y. Development of 2-DoF Adaptive Mechatronic Device with Corrective Adjustment of Laser Tracker Reflector for Industrial Robot Calibration. Annals of DAAAM & Proceedings, 2017.
Teaching
Innopolis University — Senior Lecturer (2022–present), Teaching Assistant (2019–2022)
FORC: Fundamentals of Robot Control — introductory course on state-space modeling, stability, linear and nonlinear control, and feedback linearization for robotic systems (lectures and Colab/Python labs).
- Applied Nonlinear Control; Fundamentals of Robot Control
- Modeling and Simulation of Robotic Systems; Linear Control Theory; Robotic Systems
- Computational Intelligence; Advanced Robotics
Technical Skills
Programming: Python, C/C++, Bash
Robotics & ML: MuJoCo, mjlab, Isaac Sim, Isaac Lab, RL/WBC training pipelines, system
identification
Embedded: STM32, ARM, ESP32, RP2040 (MicroPython, HAL, FreeRTOS, mbed)
Tools: Linux, LaTeX, Docker, uv, pixi
Honors
- Best Master Thesis Award, Korea University of Technology and Education, 2019
- First Prize, Russian thesis competition “Be-First” (Computer & Information Technologies), 2018
Research Interests
Articulated robots; reinforcement learning; hybrid methods; sim-to-real transfer; motion imitation; whole-body control and humanoid locomotion; learning-based and nonlinear control; system identification and estimation; differentiable simulation; data-driven motion generation.