arXiv subjects

Petar Kormushev

Publications and source records attributed to Petar Kormushev.

At least 19 recordsLinked to original sources

arXiv2026

Learning Bimanual Cloth Manipulation with Vision-based Tactile Sensing via Single Robotic Arm

Robotic cloth manipulation remains challenging due to the high-dimensional state space of fabrics, their deformable nature, and frequent occlusions that limit vision-based sensing. Although dual-arm systems can mitigate some of these issues, they increase hardware and control complexity. This paper presents Touch G.O.G., a compact vision-based tactile gripper and perception/control framework for single-arm bimanual cloth manipulation. The proposed framework combines three key components: (1) a novel gripper design and control strategy for in-gripper cloth sliding with a single robot arm, (2) a Vision Foundation Model-backboned Vision Transformer pipeline for cloth part classification (PC-Net) and edge pose estimation (PE-Net) using real and synthetic tactile images, and (3) an encoder-decoder synthetic data generator (SD-Net) that reduces manual annotation by producing high-fidelity tactile images. Experiments show 96% accuracy in distinguishing edges, corners, interior regions, and grasp failures, together with sub-millimeter edge localization and 4.5° orientation error. Real-world results demonstrate reliable cloth unfolding, even for crumpled fabrics, using only a single robotic arm. These results highlight Touch G.O.G. as a compact and cost-effective solution for deformable object manipulation.

cs.RO↗

arXiv2025

Extended Hybrid Zero Dynamics for Bipedal Walking of the Knee-less Robot SLIDER

Knee-less bipedal robots like SLIDER have the advantage of ultra-lightweight legs and improved walking energy efficiency compared to traditional humanoid robots. In this paper, we firstly introduce an improved hardware design of the SLIDER bipedal robot with new line-feet and more optimized mass distribution that enables higher locomotion speeds. Secondly, we propose an extended Hybrid Zero Dynamics (eHZD) method, which can be applied to prismatic joint robots like SLIDER. The eHZD method is then used to generate a library of gaits with varying reference velocities in an offline way. Thirdly, a Guided Deep Reinforcement Learning (DRL) algorithm is proposed to use the pre-generated library to create walking control policies in real-time. This approach allows us to combine the advantages of both HZD (for generating stable gaits with a full-dynamics model) and DRL (for real-time adaptive gait generation). The experimental results show that this approach achieves 150% higher walking velocity than the previous MPC-based approach.

cs.RO↗

arXiv2025

GraphGarment: Learning Garment Dynamics for Bimanual Cloth Manipulation Tasks

Physical manipulation of garments is often crucial when performing fabric-related tasks, such as hanging garments. However, due to the deformable nature of fabrics, these operations remain a significant challenge for robots in household, healthcare, and industrial environments. In this paper, we propose GraphGarment, a novel approach that models garment dynamics based on robot control inputs and applies the learned dynamics model to facilitate garment manipulation tasks such as hanging. Specifically, we use graphs to represent the interactions between the robot end-effector and the garment. GraphGarment uses a graph neural network (GNN) to learn a dynamics model that can predict the next garment state given the current state and input action in simulation. To address the substantial sim-to-real gap, we propose a residual model that compensates for garment state prediction errors, thereby improving real-world performance. The garment dynamics model is then applied to a model-based action sampling strategy, where it is utilized to manipulate the garment to a reference pre-hanging configuration for garment-hanging tasks. We conducted four experiments using six types of garments to validate our approach in both simulation and real-world settings. In simulation experiments, GraphGarment achieves better garment state prediction performance, with a prediction error 0.46 cm lower than the best baseline. Our approach also demonstrates improved performance in the garment-hanging simulation experiment with enhancements of 12%, 24%, and 10%, respectively. Moreover, real-world robot experiments confirm the robustness of sim-to-real transfer, with an error increase of 0.17 cm compared to simulation results. Supplementary material is available at:https://sites.google.com/view/graphgarment.

cs.RO↗

arXiv2025

A Backbone for Long-Horizon Robot Task Understanding

End-to-end robot learning, particularly for long-horizon tasks, often results in unpredictable outcomes and poor generalization. To address these challenges, we propose a novel Therblig-Based Backbone Framework (TBBF) as a fundamental structure to enhance interpretability, data efficiency, and generalization in robotic systems. TBBF utilizes expert demonstrations to enable therblig-level task decomposition, facilitate efficient action-object mapping, and generate adaptive trajectories for new scenarios. The approach consists of two stages: offline training and online testing. During the offline training stage, we developed the Meta-RGate SynerFusion (MGSF) network for accurate therblig segmentation across various tasks. In the online testing stage, after a one-shot demonstration of a new task is collected, our MGSF network extracts high-level knowledge, which is then encoded into the image using Action Registration (ActionREG). Additionally, Large Language Model (LLM)-Alignment Policy for Visual Correction (LAP-VC) is employed to ensure precise action registration, facilitating trajectory transfer in novel robot scenarios. Experimental results validate these methods, achieving 94.37% recall in therblig segmentation and success rates of 94.4% and 80% in real-world online robot testing for simple and complex scenarios, respectively. Supplementary material is available at: https://sites.google.com/view/therbligsbasedbackbone/home

cs.RO↗

arXiv2025

Haptic-ACT: Bridging Human Intuition with Compliant Robotic Manipulation via Immersive VR

Robotic manipulation is essential for the widespread adoption of robots in industrial and home settings and has long been a focus within the robotics community. Advances in artificial intelligence have introduced promising learning-based methods to address this challenge, with imitation learning emerging as particularly effective. However, efficiently acquiring high-quality demonstrations remains a challenge. In this work, we introduce an immersive VR-based teleoperation setup designed to collect demonstrations from a remote human user. We also propose an imitation learning framework called Haptic Action Chunking with Transformers (Haptic-ACT). To evaluate the platform, we conducted a pick-and-place task and collected 50 demonstration episodes. Results indicate that the immersive VR platform significantly reduces demonstrator fingertip forces compared to systems without haptic feedback, enabling more delicate manipulation. Additionally, evaluations of the Haptic-ACT framework in both the MuJoCo simulator and on a real robot demonstrate its effectiveness in teaching robots more compliant manipulation compared to the original ACT. Additional materials are available at https://sites.google.com/view/hapticact.

cs.RO↗

arXiv2025

Beyond Humanoid Prosthetic Hands: Modular Terminal Devices That Improve User Performance

Despite decades of research and development, myoelectric prosthetic hands lack functionality and are often rejected by users. This lack in functionality can be partially attributed to the widely accepted anthropomorphic design ideology in the field; attempting to replicate human hand form and function despite severe limitations in control and sensing technology. Instead, prosthetic hands can be tailored to perform specific tasks without increasing complexity by shedding the constraints of anthropomorphism. In this paper, we develop and evaluate four open-source modular non-humanoid devices to perform the motion required to replicate human flicking motion and to twist a screwdriver, and the functionality required to pick and place flat objects and to cut paper. Experimental results from these devices demonstrate that, versus a humanoid prosthesis, non-humanoid prosthesis design dramatically improves task performance, reduces user compensatory movement, and reduces task load. Case studies with two end users demonstrate the translational benefits of this research. We found that special attention should be paid to monitoring end-user task load to ensure positive rehabilitation outcomes.

cs.RO↗

arXiv2024

Examining the physical and psychological effects of combining multimodal feedback with continuous control in prosthetic hands

Myoelectric prosthetic hands are typically controlled to move between discrete positions and do not provide sensory feedback to the user. In this work, we present and evaluate a closed-loop, continuous myoelectric prosthetic hand controller, that can continuously control the position of multiple degrees of freedom of a prosthesis while rendering proprioceptive feedback to the user via a haptic feedback armband. Twenty-eight participants without and ten participants with limb difference were recruited to holistically evaluate the physical and psychological effects of the controller via isolated control and sensory tasks, dexterity assessments, embodiment and task load questionnaires, and post-study interviews. The combination of proprioceptive feedback and continuous control enabled accurate positioning, to within 10% mean absolute motor position error, and grasp-force modulation, to within 20% mean absolute motor force error, and restored blindfolded object identification ability to open-loop discrete controller levels. Dexterity assessment and embodiment questionnaire results revealed no significant physical performance or psychological embodiment differences between control types, with the exception of perceived sensation, which was significantly higher (p < 0.001) for closed-loop controllers. Key differences between participants with and without upper limb difference were identified, including in perceived body completeness and frustration, which can inform future prosthesis development and rehabilitation.

cs.RO↗

arXiv2023

The Hydra Hand: A Mode-Switching Underactuated Gripper with Precision and Power Grasping Modes

Human hands are able to grasp a wide range of object sizes, shapes, and weights, achieved via reshaping and altering their apparent grasping stiffness between compliant power and rigid precision. Achieving similar versatility in robotic hands remains a challenge, which has often been addressed by adding extra controllable degrees of freedom, tactile sensors, or specialised extra grasping hardware, at the cost of control complexity and robustness. We introduce a novel reconfigurable four-fingered two-actuator underactuated gripper -- the Hydra Hand -- that switches between compliant power and rigid precision grasps using a single motor, while generating grasps via a single hydraulic actuator -- exhibiting adaptive grasping between finger pairs, enabling the power grasping of two objects simultaneously. The mode switching mechanism and the hand's kinematics are presented and analysed, and performance is tested on two grasping benchmarks: one focused on rigid objects, and the other on items of clothing. The Hydra Hand is shown to excel at grasping large and irregular objects, and small objects with its respective compliant power and rigid precision configurations. The hand's versatility is then showcased by executing the challenging manipulation task of safely grasping and placing a bunch of grapes, and then plucking a single grape from the bunch.

cs.RO↗

arXiv2023

When and Where to Step: Terrain-Aware Real-Time Footstep Location and Timing Optimization for Bipedal Robots

Online footstep planning is essential for bipedal walking robots, allowing them to walk in the presence of disturbances and sensory noise. Most of the literature on the topic has focused on optimizing the footstep placement while keeping the step timing constant. In this work, we introduce a footstep planner capable of optimizing footstep placement and step time online. The proposed planner, consisting of an Interior Point Optimizer (IPOPT) and an optimizer based on Augmented Lagrangian (AL) method with analytical gradient descent, solves the full dynamics of the Linear Inverted Pendulum (LIP) model in real time to optimize for footstep location as well as step timing at the rate of 200~Hz. We show that such asynchronous real-time optimization with the AL method (ARTO-AL) provides the required robustness and speed for successful online footstep planning. Furthermore, ARTO-AL can be extended to plan footsteps in 3D, allowing terrain-aware footstep planning on uneven terrains. Compared to an algorithm with no footstep time adaptation, our proposed ARTO-AL demonstrates increased stability in simulated walking experiments as it can resist pushes on flat ground and on a $10^{\circ}$ ramp up to 120 N and 100 N respectively. For the video, see https://youtu.be/ABdnvPqCUu4. For code, see https://github.com/WangKeAlchemist/ARTO-AL/tree/master.

cs.RO↗

arXiv2022

OstrichRL: A Musculoskeletal Ostrich Simulation to Study Bio-mechanical Locomotion

Muscle-actuated control is a research topic that spans multiple domains, including biomechanics, neuroscience, reinforcement learning, robotics, and graphics. This type of control is particularly challenging as bodies are often overactuated and dynamics are delayed and non-linear. It is however a very well tested and tuned actuation mechanism that has undergone millions of years of evolution with interesting properties exploiting passive forces and efficient energy storage of muscle-tendon units. To facilitate research on muscle-actuated simulation, we release a 3D musculoskeletal simulation of an ostrich based on the MuJoCo physics engine. The ostrich is one of the fastest bipeds on earth and therefore makes an excellent model for studying muscle-actuated bipedal locomotion. The model is based on CT scans and dissections used to collect actual muscle data, such as insertion sites, lengths, and pennation angles. Along with this model, we also provide a set of reinforcement learning tasks, including reference motion tracking, running, and neck control, used to infer muscle actuation patterns. The reference motion data is based on motion capture clips of various behaviors that we preprocessed and adapted to our model. This paper describes how the model was built and iteratively improved using the tasks. We also evaluate the accuracy of the muscle actuation patterns by comparing them to experimentally collected electromyographic data from locomoting birds. The results demonstrate the need for rich reward signals or regularization techniques to constrain muscle excitations and produce realistic movements. Overall, we believe that this work can provide a useful bridge between fields of research interested in muscle actuation.

cs.RO↗

arXiv2022

Time Limits in Reinforcement Learning

In reinforcement learning, it is common to let an agent interact for a fixed amount of time with its environment before resetting it and repeating the process in a series of episodes. The task that the agent has to learn can either be to maximize its performance over (i) that fixed period, or (ii) an indefinite period where time limits are only used during training to diversify experience. In this paper, we provide a formal account for how time limits could effectively be handled in each of the two cases and explain why not doing so can cause state aliasing and invalidation of experience replay, leading to suboptimal policies and training instability. In case (i), we argue that the terminations due to time limits are in fact part of the environment, and thus a notion of the remaining time should be included as part of the agent's input to avoid violation of the Markov property. In case (ii), the time limits are not part of the environment and are only used to facilitate learning. We argue that this insight should be incorporated by bootstrapping from the value of the state at the end of each partial episode. For both cases, we illustrate empirically the significance of our considerations in improving the performance and stability of existing reinforcement learning algorithms, showing state-of-the-art results on several control tasks.

cs.LG↗

arXiv2021

Fast Online Optimization for Terrain-Blind Bipedal Robot Walking with a Decoupled Actuated SLIP Model

We present a highly reactive controller which enables bipedal robots to blindly walk over various kinds of uneven terrains while resisting pushes. The high level motion planner does fast online optimization for footstep locations and Center of Mass (CoM) height using the decoupled actuated Spring Loaded Inverted Pendulum (aSLIP) model. The decoupled aSLIP model simplifies the original aSLIP with Linear Inverted Pendulum (LIP) dynamics in horizontal states and spring dynamics in the vertical state. The motion planning can be formulated as a discrete-time Model Predictive Control (MPC) and solved at a frequency of 1k~HZ. The output of the motion planner using a reduced-order model is fed into an inverse-dynamics based whole body controller for execution on the robot. A key result of this controller is that the foot of the robot is compliant, which further extends the robot's ability to be robust to unobserved terrain changes. We evaluate our method in simulation with the bipedal robot SLIDER. Results show the robot can blindly walk over various uneven terrains including slopes, wave fields and stairs. It can also resist pushes while walking on uneven terrain.

cs.RO↗

arXiv2021

A Unified Model with Inertia Shaping for Highly Dynamic Jumps of Legged Robots

To achieve highly dynamic jumps of legged robots, it is essential to control the rotational dynamics of the robot. In this paper, we aim to improve the jumping performance by proposing a unified model for planning highly dynamic jumps that can approximately model the centroidal inertia. This model abstracts the robot as a single rigid body for the base and point masses for the legs. The model is called the Lump Leg Single Rigid Body Model (LL-SRBM) and can be used to plan motions for both bipedal and quadrupedal robots. By taking the effects of leg dynamics into account, LL-SRBM provides a computationally efficient way for the motion planner to change the centroidal inertia of the robot with various leg configurations. Concurrently, we propose a novel contact detection method by using the norm of the average spatial velocity. After the contact is detected, the controller is switched to force control to achieve a soft landing. Twisting jump and forward jump experiments on the bipedal robot SLIDER and quadrupedal robot ANYmal demonstrate the improved jump performance by actively changing the centroidal inertia. These experiments also show the generalization and the robustness of the integrated planning and control framework.

cs.RO↗

arXiv2021

Learning to Represent Action Values as a Hypergraph on the Action Vertices

Action-value estimation is a critical component of many reinforcement learning (RL) methods whereby sample complexity relies heavily on how fast a good estimator for action value can be learned. By viewing this problem through the lens of representation learning, good representations of both state and action can facilitate action-value estimation. While advances in deep learning have seamlessly driven progress in learning state representations, given the specificity of the notion of agency to RL, little attention has been paid to learning action representations. We conjecture that leveraging the combinatorial structure of multi-dimensional action spaces is a key ingredient for learning good representations of action. To test this, we set forth the action hypergraph networks framework -- a class of functions for learning action representations in multi-dimensional discrete action spaces with a structural inductive bias. Using this framework we realise an agent class based on a combination with deep Q-networks, which we dub hypergraph Q-networks. We show the effectiveness of our approach on a myriad of domains: illustrative prediction problems under minimal confounding effects, Atari 2600 games, and discretised physical control benchmarks.

cs.LG↗

arXiv2021

Policy Manifold Search: Exploring the Manifold Hypothesis for Diversity-based Neuroevolution

Neuroevolution is an alternative to gradient-based optimisation that has the potential to avoid local minima and allows parallelisation. The main limiting factor is that usually it does not scale well with parameter space dimensionality. Inspired by recent work examining neural network intrinsic dimension and loss landscapes, we hypothesise that there exists a low-dimensional manifold, embedded in the policy network parameter space, around which a high-density of diverse and useful policies are located. This paper proposes a novel method for diversity-based policy search via Neuroevolution, that leverages learned representations of the policy network parameters, by performing policy search in this learned representation space. Our method relies on the Quality-Diversity (QD) framework which provides a principled approach to policy search, and maintains a collection of diverse policies, used as a dataset for learning policy representations. Further, we use the Jacobian of the inverse-mapping function to guide the search in the representation space. This ensures that the generated samples remain in the high-density regions, after mapping back to the original space. Finally, we evaluate our contributions on four continuous-control tasks in simulated environments, and compare to diversity-based baselines.

cs.LG↗

arXiv2020

Policy Manifold Search for Improving Diversity-based Neuroevolution

Diversity-based approaches have recently gained popularity as an alternative paradigm to performance-based policy search. A popular approach from this family, Quality-Diversity (QD), maintains a collection of high-performing policies separated in the diversity-metric space, defined based on policies' rollout behaviours. When policies are parameterised as neural networks, i.e. Neuroevolution, QD tends to not scale well with parameter space dimensionality. Our hypothesis is that there exists a low-dimensional manifold embedded in the policy parameter space, containing a high density of diverse and feasible policies. We propose a novel approach to diversity-based policy search via Neuroevolution, that leverages learned latent representations of the policy parameters which capture the local structure of the data. Our approach iteratively collects policies according to the QD framework, in order to (i) build a collection of diverse policies, (ii) use it to learn a latent representation of the policy parameters, (iii) perform policy search in the learned latent space. We use the Jacobian of the inverse transformation (i.e.reconstruction function) to guide the search in the latent space. This ensures that the generated samples remain in the high-density regions of the original space, after reconstruction. We evaluate our contributions on three continuous control tasks in simulated environments, and compare to diversity-based baselines. The findings suggest that our approach yields a more efficient and robust policy search process.

cs.LG↗

arXiv2020

Exploring Restart Distributions

We consider the generic approach of using an experience memory to help exploration by adapting a restart distribution. That is, given the capacity to reset the state with those corresponding to the agent's past observations, we help exploration by promoting faster state-space coverage via restarting the agent from a more diverse set of initial states, as well as allowing it to restart in states associated with significant past experiences. This approach is compatible with both on-policy and off-policy methods. However, a caveat is that altering the distribution of initial states could change the optimal policies when searching within a restricted class of policies. To reduce this unsought learning bias, we evaluate our approach in deep reinforcement learning which benefits from the high representational capacity of deep neural networks. We instantiate three variants of our approach, each inspired by an idea in the context of experience replay. Using these variants, we show that performance gains can be achieved, especially in hard exploration problems.

cs.LG↗

arXiv2020

Asynchronous Real-Time Optimization of Footstep Placement and Timing in Bipedal Walking Robots

Online footstep planning is essential for bipedal walking robots to be able to walk in the presence of disturbances. Until recently this has been achieved by only optimizing the placement of the footstep, keeping the duration of the step constant. In this paper we introduce a footstep planner capable of optimizing footstep placement and timing in real-time by asynchronously combining two optimizers, which we refer to as asynchronous real-time optimization (ARTO). The first optimizer which runs at approximately 25 Hz, utilizes a fourth-order Runge-Kutta (RK4) method to accurately approximate the dynamics of the linear inverted pendulum (LIP) model for bipedal walking, then uses non-linear optimization to find optimal footsteps and duration at a lower frequency. The second optimizer that runs at approximately 250 Hz, uses analytical gradients derived from the full dynamics of the LIP model and constraint penalty terms to perform gradient descent, which finds approximately optimal footstep placement and timing at a higher frequency. By combining the two optimizers asynchronously, ARTO has the benefits of fast reactions to disturbances from the gradient descent optimizer, accurate solutions that avoid local optima from the RK4 optimizer, and increases the probability that a feasible solution will be found from the two optimizers. Experimentally, we show that ARTO is able to recover from considerably larger pushes and produces feasible solutions to larger reference velocity changes than a standard footstep location optimizer, and outperforms using just the RK4 optimizer alone.

cs.RO↗