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 1,261 records · Page 70Linked to original sources

arXiv2020

Meta-Reinforcement Learning for Robotic Industrial Insertion Tasks

Robotic insertion tasks are characterized by contact and friction mechanics, making them challenging for conventional feedback control methods due to unmodeled physical effects. Reinforcement learning (RL) is a promising approach for learning control policies in such settings. However, RL can be unsafe during exploration and might require a large amount of real-world training data, which is expensive to collect. In this paper, we study how to use meta-reinforcement learning to solve the bulk of the problem in simulation by solving a family of simulated industrial insertion tasks and then adapt policies quickly in the real world. We demonstrate our approach by training an agent to successfully perform challenging real-world insertion tasks using less than 20 trials of real-world experience. Videos and other material are available at https://pearl-insertion.github.io/

cs.LG↗

arXiv2025

Embodied Escaping: End-to-End Reinforcement Learning for Robot Navigation in Narrow Environment

Autonomous navigation is a fundamental task for robot vacuum cleaners in indoor environments. Since their core function is to clean entire areas, robots inevitably encounter dead zones in cluttered and narrow scenarios. Existing planning methods often fail to escape due to complex environmental constraints, high-dimensional search spaces, and high difficulty maneuvers. To address these challenges, this paper proposes an embodied escaping model that leverages reinforcement learning-based policy with an efficient action mask for dead zone escaping. To alleviate the issue of the sparse reward in training, we introduce a hybrid training policy that improves learning efficiency. In handling redundant and ineffective action options, we design a novel action representation to reshape the discrete action space with a uniform turning radius. Furthermore, we develop an action mask strategy to select valid action quickly, balancing precision and efficiency. In real-world experiments, our robot is equipped with a Lidar, IMU, and two-wheel encoders. Extensive quantitative and qualitative experiments across varying difficulty levels demonstrate that our robot can consistently escape from challenging dead zones. Moreover, our approach significantly outperforms compared path planning and reinforcement learning methods in terms of success rate and collision avoidance.

cs.RO↗

arXiv2026

Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair

Learning robot control policies from demonstrations is a powerful paradigm, yet real-world data is often suboptimal, noisy, or otherwise imperfect, posing significant challenges for imitation and reinforcement learning. In this work, we present a formal framework that leverages Temporal Behavior Trees (TBT), an extension of Signal Temporal Logic (STL) with Behavior Tree semantics, to repair suboptimal trajectories prior to their use in downstream policy learning. Given demonstrations that violate a TBT specification, a model-based repair algorithm corrects trajectory segments to satisfy the formal constraints, yielding a dataset that is both logically consistent and interpretable. The repaired trajectories are then used to extract potential functions that shape the reward signal for reinforcement learning, guiding the agent toward task-consistent regions of the state space without requiring knowledge of the agent's kinematic model. We demonstrate the effectiveness of this framework on discrete grid-world navigation and continuous single and multi-agent reach-avoid tasks, highlighting its potential for data-efficient robot learning in settings where high-quality demonstrations cannot be assumed.

cs.LG↗

arXiv2021

Bilateral Control-Based Imitation Learning for Velocity-Controlled Robot

Machine learning is now playing important role in robotic object manipulation. In addition, force control is necessary for manipulating various objects to achieve robustness against perturbations of configurations and stiffness. The author's group revealed that fast and dynamic object manipulation with force control can be obtained by bilateral control-based imitation learning. However, the method is applicable only in robots that can control torque, while it is not applicable in robots that can only follow position or velocity commands like many commercially available robots. Then, in this research, a way to implement bilateral control-based imitation learning to velocity-controlled robots is proposed. The validity of the proposed method is experimentally verified by a mopping task.

cs.RO↗

arXiv2024

Imitation Learning for Robotic Assisted Ultrasound Examination of Deep Venous Thrombosis using Kernelized Movement Primitives

Deep Vein Thrombosis (DVT) is a common yet potentially fatal condition, often leading to critical complications like pulmonary embolism. DVT is commonly diagnosed using Ultrasound (US) imaging, which can be inconsistent due to its high dependence on the operator's skill. Robotic US Systems (RUSs) aim to improve diagnostic test consistency but face challenges with the complex scanning pattern needed for DVT assessment, where precise control over US probe pressure is crucial for indirectly detecting occlusions. This work introduces an imitation learning method, based on Kernelized Movement Primitives (KMP), to standardize DVT US exams by training an autonomous robotic controller using sonographer demonstrations. A new recording device design enhances demonstration ergonomics, integrating with US probes and enabling seamless force and position data recording. KMPs are used to capture scanning skills, linking scan trajectory and force, enabling generalization beyond the demonstrations. Our approach, evaluated on synthetic models and volunteers, shows that the KMP-based RUS can replicate an expert's force control and image quality in DVT US examination. It outperforms previous methods using manually defined force profiles, improving exam standardization and reducing reliance on specialized sonographers.

cs.RO↗

arXiv2025

Extending Group Relative Policy Optimization to Continuous Control: A Theoretical Framework for Robotic Reinforcement Learning

Group Relative Policy Optimization (GRPO) has shown promise in discrete action spaces by eliminating value function dependencies through group-based advantage estimation. However, its application to continuous control remains unexplored, limiting its utility in robotics where continuous actions are essential. This paper presents a theoretical framework extending GRPO to continuous control environments, addressing challenges in high-dimensional action spaces, sparse rewards, and temporal dynamics. Our approach introduces trajectory-based policy clustering, state-aware advantage estimation, and regularized policy updates designed for robotic applications. We provide theoretical analysis of convergence properties and computational complexity, establishing a foundation for future empirical validation in robotic systems including locomotion and manipulation tasks.

cs.RO↗

arXiv2022

Combining Commonsense Reasoning and Knowledge Acquisition to Guide Deep Learning in Robotics

Algorithms based on deep network models are being used for many pattern recognition and decision-making tasks in robotics and AI. Training these models requires a large labeled dataset and considerable computational resources, which are not readily available in many domains. Also, it is difficult to explore the internal representations and reasoning mechanisms of these models. As a step towards addressing the underlying knowledge representation, reasoning, and learning challenges, the architecture described in this paper draws inspiration from research in cognitive systems. As a motivating example, we consider an assistive robot trying to reduce clutter in any given scene by reasoning about the occlusion of objects and stability of object configurations in an image of the scene. In this context, our architecture incrementally learns and revises a grounding of the spatial relations between objects and uses this grounding to extract spatial information from input images. Non-monotonic logical reasoning with this information and incomplete commonsense domain knowledge is used to make decisions about stability and occlusion. For images that cannot be processed by such reasoning, regions relevant to the tasks at hand are automatically identified and used to train deep network models to make the desired decisions. Image regions used to train the deep networks are also used to incrementally acquire previously unknown state constraints that are merged with the existing knowledge for subsequent reasoning. Experimental evaluation performed using simulated and real-world images indicates that in comparison with baselines based just on deep networks, our architecture improves reliability of decision making and reduces the effort involved in training data-driven deep network models.

cs.AI↗

arXiv2021

Semantic constraints to represent common sense required in household actions for multi-modal Learning-from-observation robot

The paradigm of learning-from-observation (LfO) enables a robot to learn how to perform actions by observing human-demonstrated actions. Previous research in LfO have mainly focused on the industrial domain which only consist of the observable physical constraints between a manipulating tool and the robot's working environment. In order to extend this paradigm to the household domain which consists non-observable constraints derived from a human's common sense; we introduce the idea of semantic constraints. The semantic constraints are represented similar to the physical constraints by defining a contact with an imaginary semantic environment. We thoroughly investigate the necessary and sufficient set of contact state and state transitions to understand the different types of physical and semantic constraints. We then apply our constraint representation to analyze various actions in top hit household YouTube videos and real home cooking recordings. We further categorize the frequently appearing constraint patterns into physical, semantic, and multistage task groups and verify that these groups are not only necessary but a sufficient set for covering standard household actions. Finally, we conduct a preliminary experiment using textual input to explore the possibilities of combining verbal and visual input for recognizing the task groups. Our results provide promising directions for incorporating common sense in the literature of robot teaching.

cs.RO↗

arXiv2026

Autonomously Acquiring Robot Manipulation Skills with Language-Driven Quality-Diversity

Quality-diversity (QD) algorithms have been gaining traction in robot learning, where diverse motion primitive libraries allow robots to adapt zero-shot to constraints at deployment time. However, such methods typically require expert designers to write the success condition, fitness and diversity metrics, and this strongly limits the robot's autonomy. On the other hand, existing LLM-based reward-shaping techniques allow robots to learn autonomously but only output single high-performing solutions, limiting the robot's adaptability. In this paper, we propose an approach designed to output diverse motion primitive archives by autonomously leveraging quality-diversity algorithms, only requiring a free-form description of the task in common language. To address the difficulty of designing relevant fitness and diversity metrics, we propose an autonomous exploration mechanism able to reliably output sets of functionals covering the fitness and behavior descriptor (BD) space. First, we pose policy exploration as a functional design problem, where the functional spaces are lower-dimensional than the full BD and fitness spaces, and propose an LLM-based exploration scheme to sample from these low-dimensional spaces without any task-specific prompts, fine-tuning or expert intervention. We adapt a multi-BD variant of the MAP-Elites success (MES) algorithm, designed to leverage the heterogeneous BD samples. Finally, through experiments based on the genesis simulator, we show that our method effectively generates archives of diverse motion primitives, outperforming classical QD algorithms with inferred and hand-written parametrizations on a set of $4$ robotic manipulation tasks.

cs.RO↗

arXiv2017

Deep Learning of Robotic Tasks without a Simulator using Strong and Weak Human Supervision

We propose a scheme for training a computerized agent to perform complex human tasks such as highway steering. The scheme is designed to follow a natural learning process whereby a human instructor teaches a computerized trainee. The learning process consists of five elements: (i) unsupervised feature learning; (ii) supervised imitation learning; (iii) supervised reward induction; (iv) supervised safety module construction; and (v) reinforcement learning. We implemented the last four elements of the scheme using deep convolutional networks and applied it to successfully create a computerized agent capable of autonomous highway steering over the well-known racing game Assetto Corsa. We demonstrate that the use of the last four elements is essential to effectively carry out the steering task using vision alone, without access to a driving simulator internals, and operating in wall-clock time. This is made possible also through the introduction of a safety network, a novel way for preventing the agent from performing catastrophic mistakes during the reinforcement learning stage.

cs.AI↗

arXiv2025

Merging and Disentangling Views in Visual Reinforcement Learning for Robotic Manipulation

Vision is well-known for its use in manipulation, especially using visual servoing. Due to the 3D nature of the world, using multiple camera views and merging them creates better representations for Q-learning and in turn, trains more sample efficient policies. Nevertheless, these multi-view policies are sensitive to failing cameras and can be burdensome to deploy. To mitigate these issues, we introduce a Merge And Disentanglement (MAD) algorithm that efficiently merges views to increase sample efficiency while simultaneously disentangling views by augmenting multi-view feature inputs with single-view features. This produces robust policies and allows lightweight deployment. We demonstrate the efficiency and robustness of our approach using Meta-World and ManiSkill3. For project website and code, see https://aalmuzairee.github.io/mad

cs.LG↗

arXiv2016

PlanIt: A Crowdsourcing Approach for Learning to Plan Paths from Large Scale Preference Feedback

We consider the problem of learning user preferences over robot trajectories for environments rich in objects and humans. This is challenging because the criterion defining a good trajectory varies with users, tasks and interactions in the environment. We represent trajectory preferences using a cost function that the robot learns and uses it to generate good trajectories in new environments. We design a crowdsourcing system - PlanIt, where non-expert users label segments of the robot's trajectory. PlanIt allows us to collect a large amount of user feedback, and using the weak and noisy labels from PlanIt we learn the parameters of our model. We test our approach on 122 different environments for robotic navigation and manipulation tasks. Our extensive experiments show that the learned cost function generates preferred trajectories in human environments. Our crowdsourcing system is publicly available for the visualization of the learned costs and for providing preference feedback: \url{http://planit.cs.cornell.edu}

cs.RO↗

arXiv2026

Artificial Foveated Perception for Mitigating Shortcut Learning in Robotic Foundation Models

Robotic foundation models still need task-specific fine-tuning before deployment, and the fine-tuned policies often break under modest changes in scene layout, lighting, or nearby distractors. We trace this brittleness to \textit{shortcut learning}: fine-tuning supervises actions but not the visual evidence the policy uses, so the policy can settle on scene-level correlations that predict the demonstrations without causing success. We propose Artificial Foveated Perception (AFP), a lightweight, policy-agnostic module that takes the same vision and language inputs as existing Vision-Language-Action and World Action Model pipelines and predicts task-conditioned masks over the relevant objects, the robot, and other action-critical regions. During fine-tuning the masks serve as an auxiliary grounding signal that aligns the policy's visual attention with task-relevant regions; the policy architecture is unchanged, and at inference the policy runs on the original observation stream with no AFP call in the control loop. In simulation with four robotic foundation models and on a real robot with $π_{0.5}$, AFP improves generalization under environmental perturbations, reduces overfitting, and shortens fine-tuning. Ablations over mask quality and grounding-loss design show that these gains come from directing policy learning toward task-relevant visual evidence. Code, data, and videos are available at https://apollo-lab-yale.github.io/26-CoRL-AFP-website/.

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↗

arXiv2018

Intrinsically motivated reinforcement learning for human-robot interaction in the real-world

For a natural social human-robot interaction, it is essential for a robot to learn the human-like social skills. However, learning such skills is notoriously hard due to the limited availability of direct instructions from people to teach a robot. In this paper, we propose an intrinsically motivated reinforcement learning framework in which an agent gets the intrinsic motivation-based rewards through the action-conditional predictive model. By using the proposed method, the robot learned the social skills from the human-robot interaction experiences gathered in the real uncontrolled environments. The results indicate that the robot not only acquired human-like social skills but also took more human-like decisions, on a test dataset, than a robot which received direct rewards for the task achievement.

cs.RO↗

arXiv2026

SPLC: Social Preference Learning for Crowd Robot Navigation

Offline reinforcement learning (RL) holds significant potential for crowd robot navigation in human-robot coexistence applications. However, the inherent complexity of pedestrian motion renders the design of effective reward functions for promoting socially compliant robot behaviors a persistent challenge. This paper proposes a Social Preference Learning for Crowd Robot Navigation (SPLC) algorithm to eliminate the need for detailed reward design. Its core innovation lies in the introduction of a social preference feedback mechanism to automatically generate preference data through principled preference evaluation criteria. By explicitly accounting for the intricacies of pedestrian dynamics, the pipeline mitigates the reward bias and facilitates the systematic quantification of broad social norms, thereby fostering socially compliant behaviors. Extensive experiments integrating SPLC with offline RL methods demonstrate consistent improvements over state-of-the-art baselines across standard performance metrics. Furthermore, real-world experiments on the TurtleBot4 further validate the effectiveness of SPLC in practical human-robot coexistence settings. Our code and video demos are available at https://github.com/sklus949/SPLC.

cs.RO↗

arXiv2026

Data Scaling Laws in Imitation Learning for Robotic Manipulation

Data scaling has revolutionized fields like natural language processing and computer vision, providing models with remarkable generalization capabilities. In this paper, we investigate whether similar data scaling laws exist in robotics, particularly in robotic manipulation, and whether appropriate data scaling can yield single-task robot policies that can be deployed zero-shot for any object within the same category in any environment. To this end, we conduct a comprehensive empirical study on data scaling in imitation learning. By collecting data across numerous environments and objects, we study how a policy's generalization performance changes with the number of training environments, objects, and demonstrations. Throughout our research, we collect over 40,000 demonstrations and execute more than 15,000 real-world robot rollouts under a rigorous evaluation protocol. Our findings reveal several intriguing results: the generalization performance of the policy follows a roughly power-law relationship with the number of environments and objects. The diversity of environments and objects is far more important than the absolute number of demonstrations; once the number of demonstrations per environment or object reaches a certain threshold, additional demonstrations have minimal effect. Based on these insights, we propose an efficient data collection strategy. With four data collectors working for one afternoon, we collect sufficient data to enable the policies for two tasks to achieve approximately 90% success rates in novel environments with unseen objects.

cs.RO↗

arXiv2026

An Attention-based Model for Robust Forecasting with Missing Modality

Learning with missing modalities is a fundamental challenge in multimodal robot learning, as real-world robotic systems often operate in environments with incomplete sensor data. Attention-based models are appealing for processing multimodal data because they can handle multiple modalities with a single backbone network. However, most multimodal models assume that all modalities are available during both training and inference, limiting their applicability in robotic perception and decision-making. In this paper, we introduce a multimodal model designed to handle missing modalities during both training and inference. The model is formulated as a conditional variational autoencoder (CVAE) and incorporates a transformer-based architecture that leverages attention mechanisms to learn a unified, fixed-dimensional representation, even when some modalities are missing. We show that our proposed model can be trained with missing modalities while approximating a robust representation of all modalities. We evaluate our approach on five multimodal datasets across two robot learning tasks: human trajectory prediction and robot manipulation forecasting. Experimental results demonstrate that our model effectively learns from incomplete data and is superior to prior multimodal fusion approaches.

cs.RO↗