arXiv subjects

Sethu Vijayakumar

Publications and source records attributed to Sethu Vijayakumar.

At least 19 recordsLinked to original sources

arXiv2026

BayesContact: Uncertain Pose Estimation via Visuo-Tactile Proposals and Simulation-based Inference

Contact-rich manipulation requires pose estimates that are often more accurate than what depth-only sensing provides. Existing methods, relying on vision and contact, employ costly offline training procedures that need to be retrained for new environments and geometries. We propose BayesContact, a Simulation-Based Inference framework for visuo-tactile pose estimation in peg-in-hole insertion. BayesContact maintains a particle belief over object pose and fuses depth observations with force/torque-derived contact evidence. We employ simulation based forward models to approximate these observation likelihoods. For each pose hypothesis, a renderer predicts depth measurements and a physics simulator predicts contact outcomes under guarded probing actions; both are scored against real observations to update the belief. The resulting multimodal belief also enables information-gain-based probing for active disambiguation. Across simulated geometries and real-robot experiments, BayesContact improves pose observability and insertion success over vision-only inference by 30%

cs.RO↗

arXiv2026

Optimal Transport Q-Learning for Flow Policy Steering and Acceleration

Diffusion and flow policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions, especially in the context of vision language action (VLA) models. However, high quality policy performance also requires fast inference and high quality demonstrations, which are often hard to get. Lack of these leads to suboptimal policy behaviors and failure under distribution shifts. In this work we address the problem of fine-tuning and accelerating suboptimal flow-based policies using the robot's experience through RL post-training. We introduce Optimal Transport Q-Learning (OTQL), a new method for finetuning flow policies using advantage weighted conditional optimal transport flow matching. OTQL can finetune and accelerate flows with an interaction budget of 50-60 episodes while avoiding computationally expensive distillation in simulation and real-world robot tasks. Our results show that OTQL post-trains flow policies using the robot's own experience, increasing average success percentage of single-task policies from 36% to 86% and of a pre-trained VLA from 38% to 76% while reducing the number of inference steps per action generation by 70%.

cs.RO↗

arXiv2026

roto 2.0: The Robot Tactile Olympiad

Tactile-based reinforcement learning (RL) is currently hindered by fragmented research and a focus on over-saturated orientation tasks. We introduce v2 of the Robot Tactile Olympiad (\texttt{roto 2.0}), a GPU-parallelised benchmark designed to standardise tactile-based RL across four distinct robotic morphologies (16-DOF to 24-DOF). Unlike prior benchmarks, roto focuses on end-to-end "blind" manipulation, utilising only proprioception and tactile sensing without state information or distillation. We demonstrate a significant performance leap, with our blind agents achieving 13 Baoding ball rotations in 10 seconds, an order of magnitude faster than current state-of-the-art speeds. By open-sourcing our environments and robustly tuned baselines, we reduce the barrier to entry and enable researchers to prioritise fundamental algorithmic challenges over tedious RL tuning. Website: https://elle-miller.github.io/roto/

cs.RO↗

arXiv2026

Online Estimation and Manipulation of Articulated Objects

From refrigerators to kitchen drawers, humans interact with articulated objects effortlessly every day while completing household chores. For automating these tasks, service robots must be capable of manipulating arbitrary articulated objects. Recent deep learning methods have been shown to predict valuable priors on the affordance of articulated objects from vision. In contrast, many other works estimate object articulations by observing the articulation motion, but this requires the robot to already be capable of manipulating the object. In this article, we propose a novel approach combining these methods by using a factor graph for online estimation of articulation which fuses learned visual priors and proprioceptive sensing during interaction into an analytical model of articulation based on Screw Theory. With our method, a robotic system makes an initial prediction of articulation from vision before touching the object, and then quickly updates the estimate from kinematic and force sensing during manipulation. We evaluate our method extensively in both simulations and real-world robotic manipulation experiments. We demonstrate several closed-loop estimation and manipulation experiments in which the robot was capable of opening previously unseen drawers. In real hardware experiments, the robot achieved a 75% success rate for autonomous opening of unknown articulated objects.

cs.RO↗

arXiv2025

Attentive Feature Aggregation or: How Policies Learn to Stop Worrying about Robustness and Attend to Task-Relevant Visual Cues

The adoption of pre-trained visual representations (PVRs), leveraging features from large-scale vision models, has become a popular paradigm for training visuomotor policies. However, these powerful representations can encode a broad range of task-irrelevant scene information, making the resulting trained policies vulnerable to out-of-domain visual changes and distractors. In this work we address visuomotor policy feature pooling as a solution to the observed lack of robustness in perturbed scenes. We achieve this via Attentive Feature Aggregation (AFA), a lightweight, trainable pooling mechanism that learns to naturally attend to task-relevant visual cues, ignoring even semantically rich scene distractors. Through extensive experiments in both simulation and the real world, we demonstrate that policies trained with AFA significantly outperform standard pooling approaches in the presence of visual perturbations, without requiring expensive dataset augmentation or fine-tuning of the PVR. Our findings show that ignoring extraneous visual information is a crucial step towards deploying robust and generalisable visuomotor policies. Project Page: tsagkas.github.io/afa

cs.RO↗

arXiv2025

Enhancing Tactile-based Reinforcement Learning for Robotic Control

Achieving safe, reliable real-world robotic manipulation requires agents to evolve beyond vision and incorporate tactile sensing to overcome sensory deficits and reliance on idealised state information. Despite its potential, the efficacy of tactile sensing in reinforcement learning (RL) remains inconsistent. We address this by developing self-supervised learning (SSL) methodologies to more effectively harness tactile observations, focusing on a scalable setup of proprioception and sparse binary contacts. We empirically demonstrate that sparse binary tactile signals are critical for dexterity, particularly for interactions that proprioceptive control errors do not register, such as decoupled robot-object motions. Our agents achieve superhuman dexterity in complex contact tasks (ball bouncing and Baoding ball rotation). Furthermore, we find that decoupling the SSL memory from the on-policy memory can improve performance. We release the Robot Tactile Olympiad (RoTO) benchmark to standardise and promote future research in tactile-based manipulation. Project page: https://elle-miller.github.io/tactile_rl

cs.RO↗

arXiv2025

Human-in-the-loop Optimisation in Robot-assisted Gait Training

Wearable robots offer a promising solution for quantitatively monitoring gait and providing systematic, adaptive assistance to promote patient independence and improve gait. However, due to significant interpersonal and intrapersonal variability in walking patterns, it is important to design robot controllers that can adapt to the unique characteristics of each individual. This paper investigates the potential of human-in-the-loop optimisation (HILO) to deliver personalised assistance in gait training. The Covariance Matrix Adaptation Evolution Strategy (CMA-ES) was employed to continuously optimise an assist-as-needed controller of a lower-limb exoskeleton. Six healthy individuals participated over a two-day experiment. Our results suggest that while the CMA-ES appears to converge to a unique set of stiffnesses for each individual, no measurable impact on the subjects' performance was observed during the validation trials. These findings highlight the impact of human-robot co-adaptation and human behaviour variability, whose effect may be greater than potential benefits of personalising rule-based assistive controllers. Our work contributes to understanding the limitations of current personalisation approaches in exoskeleton-assisted gait rehabilitation and identifies key challenges for effective implementation of human-in-the-loop optimisation in this domain.

cs.RO↗

arXiv2025

Assist-as-needed Control for FES in Foot Drop Management

Foot drop is commonly managed using Functional Electrical Stimulation (FES), typically delivered via open-loop controllers with fixed stimulation intensities. While users may manually adjust the intensity through external controls, this approach risks overstimulation, leading to muscle fatigue and discomfort, or understimulation, which compromises dorsiflexion and increases fall risk. In this study, we propose a novel closed-loop FES controller that dynamically adjusts the stimulation intensity based on real-time toe clearance, providing "assistance as needed". We evaluate this system by inducing foot drop in healthy participants and comparing the effects of the closed-loop controller with a traditional open-loop controller across various walking conditions, including different speeds and surface inclinations. Kinematic data reveal that our closed-loop controller maintains adequate toe clearance without significantly affecting the joint angles of the hips, the knees, and the ankles, and while using significantly lower stimulation intensities compared to the open-loop controller. These findings suggest that the proposed method not only matches the effectiveness of existing systems but also offers the potential for reduced muscle fatigue and improved long-term user comfort and adherence.

cs.RO↗

arXiv2025

Preference-Based Long-Horizon Robotic Stacking with Multimodal Large Language Models

Pretrained large language models (LLMs) can work as high-level robotic planners by reasoning over abstract task descriptions and natural language instructions, etc. However, they have shown a lack of knowledge and effectiveness in planning long-horizon robotic manipulation tasks where the physical properties of the objects are essential. An example is the stacking of containers with hidden objects inside, which involves reasoning over hidden physics properties such as weight and stability. To this end, this paper proposes to use multimodal LLMs as high-level planners for such long-horizon robotic stacking tasks. The LLM takes multimodal inputs for each object to stack and infers the current best stacking sequence by reasoning over stacking preferences. Furthermore, in order to enable the LLM to reason over multiple preferences at the same time without giving explicit instructions, we propose to create a custom dataset considering stacking preferences including weight, stability, size, and footprint, to fine-tune the LLM. Compared to the pretrained LLM with prompt tuning, we demonstrate the improved stacking completion of the LLM fine-tuned with our custom dataset via large-scale simulation evaluation. Furthermore, we showcase the effectiveness of the proposed framework for the long-horizon stacking task on a real humanoid robot in an online manner.

cs.RO↗

arXiv2025

Poke and Strike: Learning Task-Informed Exploration Policies

In many dynamic robotic tasks, such as striking pucks into a goal outside the reachable workspace, the robot must first identify the relevant physical properties of the object for successful task execution, as it is unable to recover from failure or retry without human intervention. To address this challenge, we propose a task-informed exploration approach, based on reinforcement learning, that trains an exploration policy using rewards automatically generated from the sensitivity of a privileged task policy to errors in estimated properties. We also introduce an uncertainty-based mechanism to determine when to transition from exploration to task execution, ensuring sufficient property estimation accuracy with minimal exploration time. Our method achieves a 90% success rate on the striking task with an average exploration time under 1.2 seconds, significantly outperforming baselines that achieve at most 40% success or require inefficient querying and retraining in a simulator at test time. Additionally, we demonstrate that our task-informed rewards capture the relative importance of physical properties in both the striking task and the classical CartPole example. Finally, we validate our approach by demonstrating its ability to identify object properties and adjust task execution in a physical setup using the KUKA iiwa robot arm.

cs.RO↗

arXiv2025

Scaling Whole-body Multi-contact Manipulation with Contact Optimization

Daily tasks require us to use our whole body to manipulate objects, for instance when our hands are unavailable. We consider the issue of providing humanoid robots with the ability to autonomously perform similar whole-body manipulation tasks. In this context, the infinite possibilities for where and how contact can occur on the robot and object surfaces hinder the scalability of existing planning methods, which predominantly rely on discrete sampling. Given the continuous nature of contact surfaces, gradient-based optimization offers a more suitable approach for finding solutions. However, a key remaining challenge is the lack of an efficient representation of robot surfaces. In this work, we propose (i) a representation of robot and object surfaces that enables closed-form computation of proximity points, and (ii) a cost design that effectively guides whole-body manipulation planning. Our experiments demonstrate that the proposed framework can solve problems unaddressed by existing methods, and achieves a 77% improvement in planning time over the state of the art. We also validate the suitability of our approach on real hardware through the whole-body manipulation of boxes by a humanoid robot.

cs.RO↗

arXiv2025

Few-shot transfer of tool-use skills using human demonstrations with proximity and tactile sensing

Tools extend the manipulation abilities of robots, much like they do for humans. Despite human expertise in tool manipulation, teaching robots these skills faces challenges. The complexity arises from the interplay of two simultaneous points of contact: one between the robot and the tool, and another between the tool and the environment. Tactile and proximity sensors play a crucial role in identifying these complex contacts. However, learning tool manipulation using these sensors remains challenging due to limited real-world data and the large sim-to-real gap. To address this, we propose a few-shot tool-use skill transfer framework using multimodal sensing. The framework involves pre-training the base policy to capture contact states common in tool-use skills in simulation and fine-tuning it with human demonstrations collected in the real-world target domain to bridge the domain gap. We validate that this framework enables teaching surface-following tasks using tools with diverse physical and geometric properties with a small number of demonstrations on the Franka Emika robot arm. Our analysis suggests that the robot acquires new tool-use skills by transferring the ability to recognise tool-environment contact relationships from pre-trained to fine-tuned policies. Additionally, combining proximity and tactile sensors enhances the identification of contact states and environmental geometry.

cs.RO↗

arXiv2025

Fast Flow-based Visuomotor Policies via Conditional Optimal Transport Couplings

Diffusion and flow matching policies have recently demonstrated remarkable performance in robotic applications by accurately capturing multimodal robot trajectory distributions. However, their computationally expensive inference, due to the numerical integration of an ODE or SDE, limits their applicability as real-time controllers for robots. We introduce a methodology that utilizes conditional Optimal Transport couplings between noise and samples to enforce straight solutions in the flow ODE for robot action generation tasks. We show that naively coupling noise and samples fails in conditional tasks and propose incorporating condition variables into the coupling process to improve few-step performance. The proposed few-step policy achieves a 4% higher success rate with a 10x speed-up compared to Diffusion Policy on a diverse set of simulation tasks. Moreover, it produces high-quality and diverse action trajectories within 1-2 steps on a set of real-world robot tasks. Our method also retains the same training complexity as Diffusion Policy and vanilla Flow Matching, in contrast to distillation-based approaches.

cs.RO↗

arXiv2025

ContactFusion: Stochastic Poisson Surface Maps from Visual and Contact Sensing

Robust and precise robotic assembly entails insertion of constituent components. Insertion success is hindered when noise in scene understanding exceeds tolerance limits, especially when fabricated with tight tolerances. In this work, we propose ContactFusion which combines global mapping with local contact information, fusing point clouds with force sensing. Our method entails a Rejection Sampling based contact occupancy sensing procedure which estimates contact locations on the end-effector from Force/Torque sensing at the wrist. We demonstrate how to fuse contact with visual information into a Stochastic Poisson Surface Map (SPSMap) - a map representation that can be updated with the Stochastic Poisson Surface Reconstruction (SPSR) algorithm. We first validate the contact occupancy sensor in simulation and show its ability to detect the contact location on the robot from force sensing information. Then, we evaluate our method in a peg-in-hole task, demonstrating an improvement in the hole pose estimate with the fusion of the contact information with the SPSMap.

cs.RO↗

arXiv2025

Model-based optimisation for the personalisation of robot-assisted gait training

Personalised rehabilitation can be key to promoting gait independence and quality of life. Robots can enhance therapy by systematically delivering support in gait training, but often use one-size-fits-all control methods, which can be suboptimal. Here, we describe a model-based optimisation method for designing and fine-tuning personalised robotic controllers. As a case study, we formulate the objective of providing assistance as needed as an optimisation problem, and we demonstrate how musculoskeletal modelling can be used to develop personalised interventions. Eighteen healthy participants (age = 26 +/- 4) were recruited and the personalised control parameters for each were obtained to provide assistance as needed during a unilateral tracking task. A comparison was carried out between the personalised controller and the non-personalised controller. In simulation, a significant improvement was predicted when the personalised parameters were used. Experimentally, responses varied: six subjects showed significant improvements with the personalised parameters, eight subjects showed no obvious change, while four subjects performed worse. High interpersonal and intra-personal variability was observed with both controllers. This study highlights the importance of personalised control in robot-assisted gait training, and the need for a better estimation of human-robot interaction and human behaviour to realise the benefits of model-based optimisation.

cs.RO↗

arXiv2024

Learning Visuotactile Estimation and Control for Non-prehensile Manipulation under Occlusions

Manipulation without grasping, known as non-prehensile manipulation, is essential for dexterous robots in contact-rich environments, but presents many challenges relating with underactuation, hybrid-dynamics, and frictional uncertainty. Additionally, object occlusions in a scenario of contact uncertainty and where the motion of the object evolves independently from the robot becomes a critical problem, which previous literature fails to address. We present a method for learning visuotactile state estimators and uncertainty-aware control policies for non-prehensile manipulation under occlusions, by leveraging diverse interaction data from privileged policies trained in simulation. We formulate the estimator within a Bayesian deep learning framework, to model its uncertainty, and then train uncertainty-aware control policies by incorporating the pre-learned estimator into the reinforcement learning (RL) loop, both of which lead to significantly improved estimator and policy performance. Therefore, unlike prior non-prehensile research that relies on complex external perception set-ups, our method successfully handles occlusions after sim-to-real transfer to robotic hardware with a simple onboard camera. See our video: https://youtu.be/hW-C8i_HWgs.

cs.RO↗

arXiv2024

Efficient Learning of Object Placement with Intra-Category Transfer

Efficient learning from demonstration for long-horizon tasks remains an open challenge in robotics. While significant effort has been directed toward learning trajectories, a recent resurgence of object-centric approaches has demonstrated improved sample efficiency, enabling transferable robotic skills. Such approaches model tasks as a sequence of object poses over time. In this work, we propose a scheme for transferring observed object arrangements to novel object instances by learning these arrangements on canonical class frames. We then employ this scheme to enable a simple yet effective approach for training models from as few as five demonstrations to predict arrangements of a wide range of objects including tableware, cutlery, furniture, and desk spaces. We propose a method for optimizing the learned models to enable efficient learning of tasks such as setting a table or tidying up an office with intra-category transfer, even in the presence of distractors. We present extensive experimental results in simulation and on a real robotic system for table setting which, based on human evaluations, scored 73.3% compared to a human baseline. We make the code and trained models publicly available at https://oplict.cs.uni-freiburg.de.

cs.RO↗

arXiv2024

An Efficient Representation of Whole-body Model Predictive Control for Online Compliant Dual-arm Mobile Manipulation

Dual-arm mobile manipulators can transport and manipulate large-size objects with simple end-effectors. To interact with dynamic environments with strict safety and compliance requirements, achieving whole-body motion planning online while meeting various hard constraints for such highly redundant mobile manipulators poses a significant challenge. We tackle this challenge by presenting an efficient representation of whole-body motion trajectories within our bilevel model-based predictive control (MPC) framework. We utilize B\'ezier-curve parameterization to represent the optimized collision-free trajectories of two collaborating end-effectors in the first MPC, facilitating fast long-horizon object-oriented motion planning in SE(3) while considering approximated feasibility constraints. This approach is further applied to parameterize whole-body trajectories in the second MPC for whole-body motion generation with predictive admittance control in a relatively short horizon while satisfying whole-body hard constraints. This representation enables two MPCs with continuous properties, thereby avoiding inaccurate model-state transition and dense decision-variable settings in existing MPCs using the discretization method. It strengthens the online execution of the bilevel MPC framework in high-dimensional space and facilitates the generation of consistent commands for our hybrid position/velocity-controlled robot. The simulation comparisons and real-world experiments demonstrate the efficiency and robustness of this approach in various scenarios for static and dynamic obstacle avoidance, and compliant interaction control with the manipulated object and external disturbances.

cs.RO↗