SEARCH · Search arXiv

Results for “robot learning”

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 973 records · Page 54Linked to original sources

arXiv2018

Adaptive robot body learning and estimation through predictive coding

The predictive functions that permit humans to infer their body state by sensorimotor integration are critical to perform safe interaction in complex environments. These functions are adaptive and robust to non-linear actuators and noisy sensory information. This paper introduces a computational perceptual model based on predictive processing that enables any multisensory robot to learn, infer and update its body configuration when using arbitrary sensors with Gaussian additive noise. The proposed method integrates different sources of information (tactile, visual and proprioceptive) to drive the robot belief to its current body configuration. The motivation is to enable robots with the embodied perception needed for self-calibration and safe physical human-robot interaction. We formulate body learning as obtaining the forward model that encodes the sensor values depending on the body variables, and we solve it by Gaussian process regression. We model body estimation as minimizing the discrepancy between the robot body configuration belief and the observed posterior. We minimize the variational free energy using the sensory prediction errors (sensed vs expected). In order to evaluate the model we test it on a real multisensory robotic arm. We show how different sensor modalities contributions, included as additive errors, improve the refinement of the body estimation and how the system adapts itself to provide the most plausible solution even when injecting strong sensory visuo-tactile perturbations. We further analyse the reliability of the model when different sensor modalities are disabled. This provides grounded evidence about the correctness of the perceptual model and shows how the robot estimates and adjusts its body configuration just by means of sensory information.

cs.RO↗

arXiv2026

GGraph: A GPU-Accelerated Library for Graph-Based Robot Deployment and Learning

Autonomous mobile robots require spatial representations that capture geometry and semantics while staying sparse enough for planning in large, unknown environments. Graphs provide a natural representation for this purpose and underpin both classical planning methods and a growing class of reinforcement-learning (RL) policies. However, RL training needs hundreds to thousands of parallel environments, each constructing and updating its own graph. Existing graph libraries are typically designed for either single-robot deployment or fixed graphs, and CPU-based graph construction limits scalable training to only a few dozen environments. We introduce GGraph, an open-source GPU-accelerated graph library for both robot deployment and large-scale learning. GGraph supports real robots through ROS 2 interfaces and vectorized GPU-based policy training, with built-in support for tasks including 3-D navigation, exploration, and loop-closure integration. For single-robot operation, GGraph updates graphs in milliseconds. At scale, it enables graph-based exploration policies to train across hundreds of parallel robots, reducing wall-clock training time by one order of magnitude. Across simulation and real-world experiments, these results establish GGraph as a unified graph infrastructure for both large-scale robot learning and deployment.

cs.RO↗

arXiv2026

Vision-Based Tactile Intelligence for Robotics: Sensing, Learning, and Embodied Manipulation

Tactile sensing is essential for robots in contact-rich tasks, yet many tactile sensors still provide sparse, low-dimensional signals that do not capture sufficient information for complex robotic perception and interaction. Vision-based tactile sensors (VBTSs) offer a powerful alternative by con-verting contact-induced deformation of a soft interface into im-ages. The image-based formulation gives VBTSs high-resolution, information-rich tactile observations that enable complex robotic tasks. This review surveys the full VBTS pipeline and treats sensing hardware, learning methods, simulation, and datasets as an integrated sensing-and-learning system. We 1) organize representative VBTSs into a hardware taxonomy structured by deformable elastomer design, sensor size and shape, and optical system design to guide future sensor development; 2) present a hierarchical view of learning-based tactile intelligence from low-level signal understanding to task-level policies and foundation models; and 3) examine simulation platforms and tactile datasets as a scaling layer, together with sim-to-real transfer and cross-sensor adaptation for training, benchmarking, and deployment. Finally, we identify open challenges and future directions for VBTSs in robotics. By providing a holistic view of how hardware, AI architectures, simulation, and datasets interact, this review aims to advance tactile intelligence for contact-rich robotic tasks.

cs.RO↗

arXiv2026

Formal Methods in Robot Policy Learning and Verification: A Survey on Current Techniques and Future Directions

As hardware and software systems have grown in complexity, formal methods have been indispensable tools for rigorously specifying acceptable behaviors, synthesizing programs to meet these specifications, and validating the correctness of existing programs. In the field of robotics, a similar trend of rising complexity has emerged, driven in large part by the adoption of deep learning. While this shift has enabled the development of highly performant robot policies, their implementation as deep neural networks has posed challenges to traditional formal analysis, leading to models that are inflexible, fragile, and difficult to interpret. In response, the robotics community has introduced new formal and semi-formal methods to support the precise specification of complex objectives, guide the learning process to achieve them, and enable the verification of learned policies against them. In this survey, we provide a comprehensive overview of how formal methods have been used in recent robot learning research. We organize our discussion around two pillars: policy learning and policy verification. For both, we highlight representative techniques, compare their scalability and expressiveness, and summarize how they contribute to meaningfully improving realistic robot safety and correctness. We conclude with a discussion of remaining obstacles for achieving that goal and promising directions for advancing formal methods in robot learning.

cs.RO↗

arXiv2026

RoboTales: ROBOTic Anthropomorphic LEarning Systems

RoboTales is a low-cost robotic storytelling system that animates narratives using expressive sock puppetry. Implemented autonomously on a Baxter robot as a test case, RoboTales synchronizes narration, gestures, and mouth movements to perform character-driven stories. In a pilot study, puppet-based storytelling outperformed a gesture-only mode, producing higher HRIES ratings and improved story recall, suggesting that embodied puppetry enhances engagement and narrative comprehension. Designed to be modular and platform-agnostic, RoboTales can be adapted to other manipulators and offers a screen-free alternative to passive media, supporting future deployment in child-centered learning environments.

cs.RO↗

arXiv2025

CIRO7.2: A Material Network with Circularity of -7.2 and Reinforcement-Learning-Controlled Robotic Disassembler

The competition over natural reserves of minerals is expected to increase in part because of the linear-economy paradigm based on take-make-dispose. Simultaneously, the linear economy considers end-of-use products as waste rather than as a resource, which results in large volumes of waste whose management remains an unsolved problem. Since a transition to a circular economy can mitigate these open issues, in this paper we begin by enhancing the notion of circularity based on compartmental dynamical thermodynamics, namely, $λ$, and then, we model a thermodynamical material network processing a batch of 2 solid materials of criticality coefficients of 0.1 and 0.95, with a robotic disassembler compartment controlled via reinforcement learning (RL), and processing 2-7 kg of materials. Subsequently, we focused on the design of the robotic disassembler compartment using state-of-the-art RL algorithms and assessing the algorithm performance with respect to $λ$ (Fig. 1). The highest circularity is -2.1 achieved in the case of disassembling 2 parts of 1 kg each, whereas it reduces to -7.2 in the case of disassembling 4 parts of 1 kg each contained inside a chassis of 3 kg. Finally, a sensitivity analysis highlighted that the impact on $λ$ of the performance of an RL controller has a positive correlation with the quantity and the criticality of the materials to be disassembled. This work also gives the principles of the emerging research fields indicated as circular intelligence and robotics (CIRO). Source code is publicly available.

cs.RO↗

arXiv2020

Stillleben: Realistic Scene Synthesis for Deep Learning in Robotics

Training data is the key ingredient for deep learning approaches, but difficult to obtain for the specialized domains often encountered in robotics. We describe a synthesis pipeline capable of producing training data for cluttered scene perception tasks such as semantic segmentation, object detection, and correspondence or pose estimation. Our approach arranges object meshes in physically realistic, dense scenes using physics simulation. The arranged scenes are rendered using high-quality rasterization with randomized appearance and material parameters. Noise and other transformations introduced by the camera sensors are simulated. Our pipeline can be run online during training of a deep neural network, yielding applications in life-long learning and in iterative render-and-compare approaches. We demonstrate the usability by learning semantic segmentation on the challenging YCB-Video dataset without actually using any training frames, where our method achieves performance comparable to a conventionally trained model. Additionally, we show successful application in a real-world regrasping system.

cs.CV↗

arXiv2025

Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attacks

Deep reinforcement learning (DRL) has emerged as a promising approach for robotic control, but its realworld deployment remains challenging due to its vulnerability to environmental perturbations. Existing white-box adversarial attack methods, adapted from supervised learning, fail to effectively target DRL agents as they overlook temporal dynamics and indiscriminately perturb all state dimensions, limiting their impact on long-term rewards. To address these challenges, we propose the Adaptive Gradient-Masked Reinforcement (AGMR) Attack, a white-box attack method that combines DRL with a gradient-based soft masking mechanism to dynamically identify critical state dimensions and optimize adversarial policies. AGMR selectively allocates perturbations to the most impactful state features and incorporates a dynamic adjustment mechanism to balance exploration and exploitation during training. Extensive experiments demonstrate that AGMR outperforms state-of-the-art adversarial attack methods in degrading the performance of the victim agent and enhances the victim agent's robustness through adversarial defense mechanisms.

cs.LG↗

arXiv2023

A Survey of research in Deep Learning for Robotics for Undergraduate research interns

Over the last several years, use cases for robotics based solutions have diversified from factory floors to domestic applications. In parallel, Deep Learning approaches are replacing traditional techniques in Computer Vision, Natural Language Processing, Speech processing, etc. and are delivering robust results. Our goal is to survey a number of research internship projects in the broad area of 'Deep Learning as applied to Robotics' and present a concise view for the benefit of aspiring student interns. In this paper, we survey the research work done by Robotic Institute Summer Scholars (RISS), CMU. We particularly focus on papers that use deep learning to solve core robotic problems and also robotic solutions. We trust this would be useful particularly for internship aspirants for the Robotics Institute, CMU

cs.RO↗

arXiv2017

Simultaneous active parameter estimation and control using sampling-based Bayesian reinforcement learning

Robots performing manipulation tasks must operate under uncertainty about both their pose and the dynamics of the system. In order to remain robust to modeling error and shifts in payload dynamics, agents must simultaneously perform estimation and control tasks. However, the optimal estimation actions are often not the optimal actions for accomplishing the control tasks, and thus agents trade between exploration and exploitation. This work frames the problem as a Bayes-adaptive Markov decision process and solves it online using Monte Carlo tree search and an extended Kalman filter to handle Gaussian process noise and parameter uncertainty in a continuous space. MCTS selects control actions to reduce model uncertainty and reach the goal state nearly optimally. Certainty equivalent model predictive control is used as a benchmark to compare performance in simulations with varying process noise and parameter uncertainty.

eess.SY↗

arXiv2026

PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

Robotic manipulation systems benefit from complementary sensing modalities, where each provides unique environmental information. Point clouds capture detailed geometric structure, while RGB images provide rich semantic context. Current point cloud methods struggle to capture fine-grained detail, especially for complex tasks, which RGB methods lack geometric awareness, which hinders their precision and generalization. We introduce PointMapPolicy, a novel approach that conditions diffusion policies on structured grids of points without downsampling. The resulting data type makes it easier to extract shape and spatial relationships from observations, and can be transformed between reference frames. Yet due to their structure in a regular grid, we enable the use of established computer vision techniques directly to 3D data. Using xLSTM as a backbone, our model efficiently fuses the point maps with RGB data for enhanced multi-modal perception. Through extensive experiments on the RoboCasa and CALVIN benchmarks and real robot evaluations, we demonstrate that our method achieves state-of-the-art performance across diverse manipulation tasks. The overview and demos are available on our project page: https://point-map.github.io/Point-Map/

cs.RO↗

arXiv2026

BPP: Long-Context Robot Imitation Learning by Focusing on Key History Frames

Many robot tasks require attending to the history of past observations. For example, finding an item in a room requires remembering which places have already been searched. However, the best-performing robot policies typically condition only on the current observation, limiting their applicability to such tasks. Naively conditioning on past observations often fails due to spurious correlations: policies latch onto incidental features of training histories that do not generalize to out-of-distribution trajectories upon deployment. We analyze why policies latch onto these spurious correlations and find that this problem stems from limited coverage over the space of possible histories during training, which grows exponentially with horizon. Existing regularization techniques provide inconsistent benefits across tasks, as they do not fundamentally address this coverage problem. Motivated by these findings, we propose Big Picture Policies (BPP), an approach that conditions on a minimal set of meaningful keyframes detected by a vision-language model. By projecting diverse rollouts onto a compact set of task-relevant events, BPP substantially reduces distribution shift between training and deployment, without sacrificing expressivity. We evaluate BPP on four challenging real-world manipulation tasks and three simulation tasks, all requiring history conditioning. BPP achieves 70% higher success rates than the best comparison on real-world evaluations. Videos are available at https://bigpicturepolicies.github.io/

cs.RO↗

arXiv2026

More Structure, Not More Capacity: Object-Centric Representations for Visuomotor Imitation Learning

Robotic manipulation policies rely on pre-trained vision models that give either a global scene embedding or a dense patch grid. Both mix task-relevant and task-irrelevant features. Object-centric slot representations are a structured alternative: they group features into a few per-object slots. We test what this structure buys on ManiSkill3 PickCube-v1, with a frozen encoder and a held-out-seed evaluation. Holding the policy, goal token, rendering, and calibration fixed and changing only the encoder, a frozen object-centric SPOT representation (DINO ViT-B/16 + Slot Attention) reaches 55.0$\pm$2.9% success, 22.4% above a dense DINO global-feature baseline (32.6 $\pm$ 1.5%), with the same trainable policy and no encoder fine-tuning. More tokens alone do not help: a dense patch grid with 16x the tokens performs no better than the global feature. Adding an explicit 2D spatial goal and native-resolution rendering raises the full system to 68.7$\pm$4.2%, just below a privileged 3D-oracle upper bound (71.7$\pm$4.1%). An automated kinematic failure taxonomy then separates spatial-precision (Near-Miss) failures from object-tracking (No-Grasp) failures: spatial grounding reduces Near-Miss while leaving No- Grasp unchanged. The same taxonomy transfers to the harder StackCube-v1 and points to occlusion as the main bottleneck.

cs.RO↗

arXiv2026

PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning

Robotic manipulation often contains repeated motions whose local observations look similar at different phases. When these phases require different actions, a policy that relies mainly on the current observation may repeat completed motions or switch phases at the wrong time. To address this phase ambiguity, we present the Pseudo-Memory Temporal Re-encoding Module (PMTRM), a lightweight plug-in module with only 7.61M parameters that encodes a bounded history of executed states and actions into a latent sequence for existing policies. To help distinguish phases, a temporal heterogeneity objective penalizes positive similarity between distant positions in this sequence, while anchor and reconstruction losses preserve information needed for action prediction. The reconstruction decoder is used only during training, leaving the temporal re-encoder to supply history to the policy at inference. We train the module progressively on synthetic sequences and robot data, then jointly with the policy, using temporal masking to accommodate partial histories. This integration retains the original action head and action space and adds auxiliary losses to the original policy loss. Experiments with multiple policy backbones in simulation and on a real robot show improved task success on tasks with phase ambiguity, with little additional computation.

cs.RO↗

arXiv2025

IMA-Catcher: An IMpact-Aware Nonprehensile Catching Framework based on Combined Optimization and Learning

Robotic catching of flying objects typically generates high impact forces that might lead to task failure and potential hardware damages. This is accentuated when the object mass to robot payload ratio increases, given the strong inertial components characterizing this task. This paper aims to address this problem by proposing an implicitly impact-aware framework that accomplishes the catching task in both pre- and post-catching phases. In the first phase, a motion planner generates optimal trajectories that minimize catching forces, while in the second, the object's energy is dissipated smoothly, minimizing bouncing. In particular, in the pre-catching phase, a real-time optimal planner is responsible for generating trajectories of the end-effector that minimize the velocity difference between the robot and the object to reduce impact forces during catching. In the post-catching phase, the robot's position, velocity, and stiffness trajectories are generated based on human demonstrations when catching a series of free-falling objects with unknown masses. A hierarchical quadratic programming-based controller is used to enforce the robot's constraints (i.e., joint and torque limits) and create a stack of tasks that minimizes the reflected mass at the end-effector as a secondary objective. The initial experiments isolate the problem along one dimension to accurately study the effects of each contribution on the metrics proposed. We show how the same task, without velocity matching, would be infeasible due to excessive joint torques resulting from the impact. The addition of reflected mass minimization is then investigated, and the catching height is increased to evaluate the method's robustness. Finally, the setup is extended to catching along multiple Cartesian axes, to prove its generalization in space.

cs.RO↗

arXiv2019

Feature-Based Transfer Learning for Robotic Push Manipulation

This paper presents a data-efficient approach to learning transferable forward models for robotic push manipulation. Our approach extends our previous work on contact-based predictors by leveraging information on the pushed object's local surface features. We test the hypothesis that, by conditioning predictions on local surface features, we can achieve generalisation across objects of different shapes. In doing so, we do not require a CAD model of the object but rather rely on a point cloud object model (PCOM). Our approach involves learning motion models that are specific to contact models. Contact models encode the contacts seen during training time and allow generating similar contacts at prediction time. Predicting on familiar ground reduces the motion models' sample complexity while using local contact information for prediction increases their transferability. In extensive experiments in simulation, our approach is capable of transfer learning for various test objects, outperforming a baseline predictor. We support those results with a proof of concept on a real robot.

cs.RO↗

arXiv2020

Open-Sourced Reinforcement Learning Environments for Surgical Robotics

Reinforcement Learning (RL) is a machine learning framework for artificially intelligent systems to solve a variety of complex problems. Recent years has seen a surge of successes solving challenging games and smaller domain problems, including simple though non-specific robotic manipulation and grasping tasks. Rapid successes in RL have come in part due to the strong collaborative effort by the RL community to work on common, open-sourced environment simulators such as OpenAI's Gym that allow for expedited development and valid comparisons between different, state-of-art strategies. In this paper, we aim to start the bridge between the RL and the surgical robotics communities by presenting the first open-sourced reinforcement learning environments for surgical robots, called dVRL[3]{dVRL available at https://github.com/ucsdarclab/dVRL}. Through the proposed RL environments, which are functionally equivalent to Gym, we show that it is easy to prototype and implement state-of-art RL algorithms on surgical robotics problems that aim to introduce autonomous robotic precision and accuracy to assisting, collaborative, or repetitive tasks during surgery. Learned policies are furthermore successfully transferable to a real robot. Finally, combining dVRL with the over 40+ international network of da Vinci Surgical Research Kits in active use at academic institutions, we see dVRL as enabling the broad surgical robotics community to fully leverage the newest strategies in reinforcement learning, and for reinforcement learning scientists with no knowledge of surgical robotics to test and develop new algorithms that can solve the real-world, high-impact challenges in autonomous surgery.

cs.RO↗

arXiv2017

One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay

Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is that interaction with the real world is costly, but training on limited experience is prone to overfitting. We present a method for learning to navigate, to a fixed goal and in a known environment, on a mobile robot. The robot leverages an interactive world model built from a single traversal of the environment, a pre-trained visual feature encoder, and stochastic environmental augmentation, to demonstrate successful zero-shot transfer under real-world environmental variations without fine-tuning.

cs.AI↗