arXiv subjects

Todor Stoyanov

Publications and source records attributed to Todor Stoyanov.

At least 19 recordsLinked to original sources

arXiv2026

Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity Recognition

This paper addresses the problem of Human Activity Recognition (HAR) using data from wearable inertial sensors. An important challenge in HAR is the model's generalization capabilities to new unseen individuals due to inter-subject variability, i.e., the same activity is performed differently by different individuals. To address this problem, we propose a novel deep adversarial framework that integrates the concept of inter-subject variability in the adversarial task, thereby encouraging subject-invariant feature representations and enhancing the classification performance in the HAR problem. Our approach outperforms previous methods in three well-established HAR datasets using a leave-one-subject-out (LOSO) cross-validation. Further results indicate that our proposed adversarial task effectively reduces inter-subject variability among different users in the feature space, and it outperforms adversarial tasks from previous works when integrated into our framework. Code: https://github.com/FranciscoCalatrava/EmbeddedSubjectVariability.git

cs.LG↗

arXiv2025

Single-View Shape Completion for Robotic Grasping in Clutter

In vision-based robot manipulation, a single camera view can only capture one side of objects of interest, with additional occlusions in cluttered scenes further restricting visibility. As a result, the observed geometry is incomplete, and grasp estimation algorithms perform suboptimally. To address this limitation, we leverage diffusion models to perform category-level 3D shape completion from partial depth observations obtained from a single view, reconstructing complete object geometries to provide richer context for grasp planning. Our method focuses on common household items with diverse geometries, generating full 3D shapes that serve as input to downstream grasp inference networks. Unlike prior work, which primarily considers isolated objects or minimal clutter, we evaluate shape completion and grasping in realistic clutter scenarios with household objects. In preliminary evaluations on a cluttered scene, our approach consistently results in better grasp success rates than a naive baseline without shape completion by 23% and over a recent state of the art shape completion approach by 19%. Our code is available at https://amm.aass.oru.se/shape-completion-grasping/.

cs.RO↗

arXiv2025

Can Context Bridge the Reality Gap? Sim-to-Real Transfer of Context-Aware Policies

Sim-to-real transfer remains a major challenge in reinforcement learning (RL) for robotics, as policies trained in simulation often fail to generalize to the real world due to discrepancies in environment dynamics. Domain Randomization (DR) mitigates this issue by exposing the policy to a wide range of randomized dynamics during training, yet leading to a reduction in performance. While standard approaches typically train policies agnostic to these variations, we investigate whether sim-to-real transfer can be improved by conditioning the policy on an estimate of the dynamics parameters -- referred to as context. To this end, we integrate a context estimation module into a DR-based RL framework and systematically compare SOTA supervision strategies. We evaluate the resulting context-aware policies in both a canonical control benchmark and a real-world pushing task using a Franka Emika Panda robot. Results show that context-aware policies outperform the context-agnostic baseline across all settings, although the best supervision strategy depends on the task.

cs.RO↗

arXiv2025

KEA: Keeping Exploration Alive by Proactively Coordinating Exploration Strategies

Soft Actor-Critic (SAC) has achieved notable success in continuous control tasks but struggles in sparse reward settings, where infrequent rewards make efficient exploration challenging. While novelty-based exploration methods address this issue by encouraging the agent to explore novel states, they are not trivial to apply to SAC. In particular, managing the interaction between novelty-based exploration and SAC's stochastic policy can lead to inefficient exploration and redundant sample collection. In this paper, we propose KEA (Keeping Exploration Alive) which tackles the inefficiencies in balancing exploration strategies when combining SAC with novelty-based exploration. KEA integrates a novelty-augmented SAC with a standard SAC agent, proactively coordinated via a switching mechanism. This coordination allows the agent to maintain stochasticity in high-novelty regions, enhancing exploration efficiency and reducing repeated sample collection. We first analyze this potential issue in a 2D navigation task, and then evaluate KEA on the DeepSea hard-exploration benchmark as well as sparse reward control tasks from the DeepMind Control Suite. Compared to state-of-the-art novelty-based exploration baselines, our experiments show that KEA significantly improves learning efficiency and robustness in sparse reward setups.

cs.LG↗

arXiv2025

Exploiting Radiance Fields for Grasp Generation on Novel Synthetic Views

Vision based robot manipulation uses cameras to capture one or more images of a scene containing the objects to be manipulated. Taking multiple images can help if any object is occluded from one viewpoint but more visible from another viewpoint. However, the camera has to be moved to a sequence of suitable positions for capturing multiple images, which requires time and may not always be possible, due to reachability constraints. So while additional images can produce more accurate grasp poses due to the extra information available, the time-cost goes up with the number of additional views sampled. Scene representations like Gaussian Splatting are capable of rendering accurate photorealistic virtual images from user-specified novel viewpoints. In this work, we show initial results which indicate that novel view synthesis can provide additional context in generating grasp poses. Our experiments on the Graspnet-1billion dataset show that novel views contributed force-closure grasps in addition to the force-closure grasps obtained from sparsely sampled real views while also improving grasp coverage. In the future we hope this work can be extended to improve grasp extraction from radiance fields constructed with a single input image, using for example diffusion models or generalizable radiance fields.

cs.RO↗

arXiv2025

Beyond Predefined Actions: Integrating Behavior Trees and Dynamic Movement Primitives for Robot Learning from Demonstration

Interpretable policy representations like Behavior Trees (BTs) and Dynamic Motion Primitives (DMPs) enable robot skill transfer from human demonstrations, but each faces limitations: BTs require expert-crafted low-level actions, while DMPs lack high-level task logic. We address these limitations by integrating DMP controllers into a BT framework, jointly learning the BT structure and DMP actions from single demonstrations, thereby removing the need for predefined actions. Additionally, by combining BT decision logic with DMP motion generation, our method enhances policy interpretability, modularity, and adaptability for autonomous systems. Our approach readily affords both learning to replicate low-level motions and combining partial demonstrations into a coherent and easy-to-modify overall policy.

cs.RO↗

arXiv2025

On the Fly Adaptation of Behavior Tree-Based Policies through Reinforcement Learning

With the rising demand for flexible manufacturing, robots are increasingly expected to operate in dynamic environments where local -- such as slight offsets or size differences in workpieces -- are common. We propose to address the problem of adapting robot behaviors to these task variations with a sample-efficient hierarchical reinforcement learning approach adapting Behavior Tree (BT)-based policies. We maintain the core BT properties as an interpretable, modular framework for structuring reactive behaviors, but extend their use beyond static tasks by inherently accommodating local task variations. To show the efficiency and effectiveness of our approach, we conduct experiments both in simulation and on a Franka Emika Panda 7-DoF, with the manipulator adapting to different obstacle avoidance and pivoting tasks.

cs.RO↗

arXiv2024

Hidden in Plain Sound: Environmental Backdoor Poisoning Attacks on Whisper, and Mitigations

Thanks to the popularisation of transformer-based models, speech recognition (SR) is gaining traction in various application fields, such as industrial and robotics environments populated with mission-critical devices. While transformer-based SR can provide various benefits for simplifying human-machine interfacing, the research on the cybersecurity aspects of these models is lacklustre. In particular, concerning backdoor poisoning attacks. In this paper, we propose a new poisoning approach that maps different environmental trigger sounds to target phrases of different lengths, during the fine-tuning phase. We test our approach on Whisper, one of the most popular transformer-based SR model, showing that it is highly vulnerable to our attack, under several testing conditions. To mitigate the attack proposed in this paper, we investigate the use of Silero VAD, a state-of-the-art voice activity detection (VAD) model, as a defence mechanism. Our experiments show that it is possible to use VAD models to filter out malicious triggers and mitigate our attacks, with a varying degree of success, depending on the type of trigger sound and testing conditions.

cs.CR↗

arXiv2024

Learning Extrinsic Dexterity with Parameterized Manipulation Primitives

Many practically relevant robot grasping problems feature a target object for which all grasps are occluded, e.g., by the environment. Single-shot grasp planning invariably fails in such scenarios. Instead, it is necessary to first manipulate the object into a configuration that affords a grasp. We solve this problem by learning a sequence of actions that utilize the environment to change the object's pose. Concretely, we employ hierarchical reinforcement learning to combine a sequence of learned parameterized manipulation primitives. By learning the low-level manipulation policies, our approach can control the object's state through exploiting interactions between the object, the gripper, and the environment. Designing such a complex behavior analytically would be infeasible under uncontrolled conditions, as an analytic approach requires accurate physical modeling of the interaction and contact dynamics. In contrast, we learn a hierarchical policy model that operates directly on depth perception data, without the need for object detection, pose estimation, or manual design of controllers. We evaluate our approach on picking box-shaped objects of various weight, shape, and friction properties from a constrained table-top workspace. Our method transfers to a real robot and is able to successfully complete the object picking task in 98\% of experimental trials. Supplementary information and videos can be found at https://shihminyang.github.io/ED-PMP/.

cs.RO↗

arXiv2023

Sensors for Mobile Robots

A sensor is a device that converts a physical parameter or an environmental characteristic (e.g., temperature, distance, speed, etc.) into a signal that can be digitally measured and processed to perform specific tasks. Mobile robots need sensors to measure properties of their environment, thus allowing for safe navigation, complex perception and corresponding actions, and effective interactions with other agents that populate it. Sensors used by mobile robots range from simple tactile sensors, such as bumpers, to complex vision-based sensors such as structured light RGB-D cameras. All of them provide a digital output (e.g., a string, a set of values, a matrix, etc.) that can be processed by the robot's computer. Such output is typically obtained by discretizing one or more analog electrical signals by using an Analog to Digital Converter (ADC) included in the sensor. In this chapter we present the most common sensors used in mobile robotics, providing an introduction to their taxonomy, basic features, and specifications. The description of the functionalities and the types of applications follows a bottom-up approach: the basic principles and components on which the sensors are based are presented before describing real-world sensors, which are generally based on multiple technologies and basic devices.

cs.RO↗

arXiv2023

Software Architectures for Mobile Robots

A software architecture defines the blueprints of a large computational system, and is thus a crucial part of the design and development effort. This task has been explored extensively in the context of mobile robots, resulting in a plethora of reference designs and implementations. As the software architecture defines the framework in which all components are implemented, it is naturally a very important aspect of a mobile robot system. In this chapter, we overview the requirements that the particular problem domain (a mobile robot system) imposes on the software framework. We discuss some of the current design solutions, provide a historical perspective on common frameworks, and outline directions for future development.

cs.RO↗

arXiv2022

Heterogeneous Full-body Control of a Mobile Manipulator with Behavior Trees

Integrating the heterogeneous controllers of a complex mechanical system, such as a mobile manipulator, within the same structure and in a modular way is still challenging. In this work we extend our framework based on Behavior Trees for the control of a redundant mechanical system to the problem of commanding more complex systems that involve multiple low-level controllers. This allows the integrated systems to achieve non-trivial goals that require coordination among the sub-systems.

cs.RO↗

arXiv2022

Towards Task-Prioritized Policy Composition

Combining learned policies in a prioritized, ordered manner is desirable because it allows for modular design and facilitates data reuse through knowledge transfer. In control theory, prioritized composition is realized by null-space control, where low-priority control actions are projected into the null-space of high-priority control actions. Such a method is currently unavailable for Reinforcement Learning. We propose a novel, task-prioritized composition framework for Reinforcement Learning, which involves a novel concept: The indifferent-space of Reinforcement Learning policies. Our framework has the potential to facilitate knowledge transfer and modular design while greatly increasing data efficiency and data reuse for Reinforcement Learning agents. Further, our approach can ensure high-priority constraint satisfaction, which makes it promising for learning in safety-critical domains like robotics. Unlike null-space control, our approach allows learning globally optimal policies for the compound task by online learning in the indifference-space of higher-level policies after initial compound policy construction.

cs.LG↗

arXiv2022

Transferring Knowledge for Reinforcement Learning in Contact-Rich Manipulation

In manufacturing, assembly tasks have been a challenge for learning algorithms due to variant dynamics of different environments. Reinforcement learning (RL) is a promising framework to automatically learn these tasks, yet it is still not easy to apply a learned policy or skill, that is the ability of solving a task, to a similar environment even if the deployment conditions are only slightly different. In this paper, we address the challenge of transferring knowledge within a family of similar tasks by leveraging multiple skill priors. We propose to learn prior distribution over the specific skill required to accomplish each task and compose the family of skill priors to guide learning the policy for a new task by comparing the similarity between the target task and the prior ones. Our method learns a latent action space representing the skill embedding from demonstrated trajectories for each prior task. We have evaluated our method on a set of peg-in-hole insertion tasks and demonstrate better generalization to new tasks that have never been encountered during training.

cs.RO↗

arXiv2022

A Stack-of-Tasks Approach Combined with Behavior Trees: a New Framework for Robot Control

Stack-of-Tasks (SoT) control allows a robot to simultaneously fulfill a number of prioritized goals formulated in terms of (in)equality constraints in error space. Since this approach solves a sequence of Quadratic Programs (QP) at each time-step, without taking into account any temporal state evolution, it is suitable for dealing with local disturbances. However, its limitation lies in the handling of situations that require non-quadratic objectives to achieve a specific goal, as well as situations where countering the control disturbance would require a locally suboptimal action. Recent works address this shortcoming by exploiting Finite State Machines (FSMs) to compose the tasks in such a way that the robot does not get stuck in local minima. Nevertheless, the intrinsic trade-off between reactivity and modularity that characterizes FSMs makes them impractical for defining reactive behaviors in dynamic environments. In this letter, we combine the SoT control strategy with Behavior Trees (BTs), a task switching structure that addresses some of the limitations of the FSMs in terms of reactivity, modularity and re-usability. Experimental results on a Franka Emika Panda 7-DOF manipulator show the robustness of our framework, that allows the robot to benefit from the reactivity of both SoT and BTs.

cs.RO↗

arXiv2020

Ensemble of Sparse Gaussian Process Experts for Implicit Surface Mapping with Streaming Data

Creating maps is an essential task in robotics and provides the basis for effective planning and navigation. In this paper, we learn a compact and continuous implicit surface map of an environment from a stream of range data with known poses. For this, we create and incrementally adjust an ensemble of approximate Gaussian process (GP) experts which are each responsible for a different part of the map. Instead of inserting all arriving data into the GP models, we greedily trade-off between model complexity and prediction error. Our algorithm therefore uses less resources on areas with few geometric features and more where the environment is rich in variety. We evaluate our approach on synthetic and real-world data sets and analyze sensitivity to parameters and measurement noise. The results show that we can learn compact and accurate implicit surface models under different conditions, with a performance comparable to or better than that of exact GP regression with subsampled data.

cs.LG↗

arXiv2019

High-quality Instance-aware Semantic 3D Map Using RGB-D Camera

We present a mapping system capable of constructing detailed instance-level semantic models of room-sized indoor environments by means of an RGB-D camera. In this work, we integrate deep-learning-based instance segmentation and classification into a state of the art RGB-D SLAM system. We leverage the pipeline of ElasticFusion [1] as a backbone and propose modifications of the registration cost function. The proposed objective function features a tunable weight for the appearance channel, which can be learned from data. The resulting system is capable of producing accurate semantic maps of room-sized environments, as well as reconstructing highly detailed object-level models. The developed method has been verified through experimental validation on the TUMRGB-D SLAM benchmark and the YCB video dataset. Our results confirmed that the proposed system performs favorably in terms of trajectory estimation, surface reconstruction, and segmentation quality in comparison to other state-of-the-art systems.

cs.RO↗

arXiv2019

Object-RPE: Dense 3D Reconstruction and Pose Estimation with Convolutional Neural Networks for Warehouse Robots

We present an approach for recognizing all objects in a scene and estimating their full pose from an accurate 3D instance-aware semantic reconstruction using an RGB-D camera. Our framework couples convolutional neural networks (CNNs) and a state-of-the-art dense Simultaneous Localisation and Mapping (SLAM) system, ElasticFusion, to achieve both high-quality semantic reconstruction as well as robust 6D pose estimation for relevant objects. While the main trend in CNN-based 6D pose estimation has been to infer object's position and orientation from single views of the scene, our approach explores performing pose estimation from multiple viewpoints, under the conjecture that combining multiple predictions can improve the robustness of an object detection system. The resulting system is capable of producing high-quality object-aware semantic reconstructions of room-sized environments, as well as accurately detecting objects and their 6D poses. The developed method has been verified through experimental validation on the YCB-Video dataset and a newly collected warehouse object dataset. Experimental results confirmed that the proposed system achieves improvements over state-of-the-art methods in terms of surface reconstruction and object pose prediction. Our code and video are available at https://sites.google.com/view/object-rpe.

cs.RO↗