SEARCH · Searcharxiv

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 577 records · Page 32Linked to original sources

arXiv2026

One Demonstration Is Enough for Real-World Robotic Reinforcement Learning

Learning effective robot control policies on physical hardware is challenging due to costly data collection and the difficulty of reward specification. Prior work has incorporated demonstrations into reinforcement learning (RL), yet existing approaches either require large numbers of demonstrations or depend on continuous human intervention during training. To address these limitations, we present AutoSERL, a framework that leverages a single demonstration to fully automate the intervention process in real-world robot RL. The framework includes three complementary mechanisms to accomplish certain tasks: a sliding window intervention mechanism that continuously guides exploration to prevent local optima and unsafe deviations, a safety recovery mechanism that detects and corrects failure states via predefined trajectory recovery points, and an intervention termination criterion that automatically disables guidance once the policy can independently complete the task, preserving its exploration advantage. We evaluate AutoSERL on six contact-intensive manipulation tasks across two robot platforms, spanning insertion, hanging, and hinge-based tasks. AutoSERL consistently outperforms SERL initialized with 20 demonstrations, behavior cloning, and MILES -- a dedicated one-shot imitation learning baseline -- across all tasks while matching HIL-SERL, achieves 100% success rate on insertion tasks, and demonstrates improved robustness to positional variations, all from a single demonstration. Code and videos are available on our project website: https://autoserl.github.io/.

cs.RO↗

arXiv2025

Steering Your Diffusion Policy with Latent Space Reinforcement Learning

Robotic control policies learned from human demonstrations have achieved impressive results in many real-world applications. However, in scenarios where initial performance is not satisfactory, as is often the case in novel open-world settings, such behavioral cloning (BC)-learned policies typically require collecting additional human demonstrations to further improve their behavior -- an expensive and time-consuming process. In contrast, reinforcement learning (RL) holds the promise of enabling autonomous online policy improvement, but often falls short of achieving this due to the large number of samples it typically requires. In this work we take steps towards enabling fast autonomous adaptation of BC-trained policies via efficient real-world RL. Focusing in particular on diffusion policies -- a state-of-the-art BC methodology -- we propose diffusion steering via reinforcement learning (DSRL): adapting the BC policy by running RL over its latent-noise space. We show that DSRL is highly sample efficient, requires only black-box access to the BC policy, and enables effective real-world autonomous policy improvement. Furthermore, DSRL avoids many of the challenges associated with finetuning diffusion policies, obviating the need to modify the weights of the base policy at all. We demonstrate DSRL on simulated benchmarks, real-world robotic tasks, and for adapting pretrained generalist policies, illustrating its sample efficiency and effective performance at real-world policy improvement.

cs.RO↗

arXiv2026

SPACE: Enabling Learning from Cross-Robot Data Toward Generalist Policies

In robot learning, scaling training datasets across diverse embodiments and environments has become a dominant paradigm for learning generalizable robot policies. These policies are commonly trained via behavior cloning to imitate actions from pre-collected demonstrations. However, since robot actions are tied to the dynamics of the data collection robot, different robots may require different actions to achieve the same motion. This discrepancy hinders both policy training and deployment across diverse robots. To address this, we propose using Cartesian state delta as a universal action representation across robots, and introduce State Prediction and Adaptive Command Execution (SPACE) framework. SPACE handles robot dynamics variation at three levels: across different embodiments, across hardware units of the same embodiment, and within a single robot during operation. It consists of two components: (i) a Cartesian state delta policy that predicts geometric end-effector displacement, and (ii) Action Adapter, which converts the predicted Cartesian state delta into robot-specific control commands. Experiments show that SPACE substantially outperforms policies that directly predict control commands when learning from data collected across different embodiments and across hardware units of the same embodiment. SPACE also remains robust under dynamics shifts at deployment, including changes in control frequency, object weight, and controller gains. The project page is available at http://haeone.site/space-website/.

cs.RO↗

arXiv2026

CroSTAta: Cross-State Transition Attention Transformer for Robotic Manipulation

Learning robotic manipulation policies through supervised learning from demonstrations remains challenging when policies encounter execution variations not explicitly covered during training. While incorporating historical context through attention mechanisms can improve robustness, standard approaches process all past states in a sequence without explicitly modeling the temporal structure that demonstrations may include, such as failure and recovery patterns. We propose a Cross-State Transition Attention Transformer that employs a novel State Transition Attention (STA) mechanism to modulate standard attention weights based on learned state evolution patterns, enabling policies to better adapt their behavior based on execution history. Our approach combines this structured attention with temporal masking during training, where visual information is randomly removed from recent timesteps to encourage temporal reasoning from historical context. Evaluation in simulation shows that STA consistently outperforms standard attention approach and temporal modeling methods like TCN and LSTM networks, achieving more than 2x improvement over cross-attention on precision-critical tasks. The source code and data can be accessed at https://github.com/iit-DLSLab/croSTAta

cs.RO↗

arXiv2017

Robot Composite Learning and the Nunchaku Flipping Challenge

Advanced motor skills are essential for robots to physically coexist with humans. Much research on robot dynamics and control has achieved success on hyper robot motor capabilities, but mostly through heavily case-specific engineering. Meanwhile, in terms of robot acquiring skills in a ubiquitous manner, robot learning from human demonstration (LfD) has achieved great progress, but still has limitations handling dynamic skills and compound actions. In this paper, we present a composite learning scheme which goes beyond LfD and integrates robot learning from human definition, demonstration, and evaluation. The method tackles advanced motor skills that require dynamic time-critical maneuver, complex contact control, and handling partly soft partly rigid objects. We also introduce the "nunchaku flipping challenge", an extreme test that puts hard requirements to all these three aspects. Continued from our previous presentations, this paper introduces the latest update of the composite learning scheme and the physical success of the nunchaku flipping challenge.

cs.RO↗

arXiv2026

SurgVIL: Scaling Surgical Robot Imitation Learning with Open-source Surgical Videos

Learning-based surgical robot autonomy requires large-scale demonstrations with synchronized videos and robot actions, but such data are exceedingly rare in clinical or realistic tissue settings because robot kinematics are typically inaccessible outside controlled research systems. In contrast, phantom data collected on research platforms provide accurate action labels but lack the visual diversity of real tissue. We propose SurgVIL, a framework for scaling surgical robot imitation learning using open-source surgical videos. SurgVIL combines kinematically labeled phantom robot demonstrations with surgical videos from open-source datasets and online sources for policy learning. Since these videos lack robot motion labels, we estimate approximate kinematics as weak supervision. We evaluate SurgVIL on two da Vinci robot tasks: needle pick-up and cholecystectomy cutting. Across ACT, $π_0$, and GR00T-H backbones, adding surgical videos substantially improves generalization to real-tissue and out-of-distribution settings, suggesting a scalable path from phantom training toward generalizable surgical robot policies.

cs.RO↗

arXiv2022

i-Sim2Real: Reinforcement Learning of Robotic Policies in Tight Human-Robot Interaction Loops

Sim-to-real transfer is a powerful paradigm for robotic reinforcement learning. The ability to train policies in simulation enables safe exploration and large-scale data collection quickly at low cost. However, prior works in sim-to-real transfer of robotic policies typically do not involve any human-robot interaction because accurately simulating human behavior is an open problem. In this work, our goal is to leverage the power of simulation to train robotic policies that are proficient at interacting with humans upon deployment. But there is a chicken and egg problem -- how to gather examples of a human interacting with a physical robot so as to model human behavior in simulation without already having a robot that is able to interact with a human? Our proposed method, Iterative-Sim-to-Real (i-S2R), attempts to address this. i-S2R bootstraps from a simple model of human behavior and alternates between training in simulation and deploying in the real world. In each iteration, both the human behavior model and the policy are refined. For all training we apply a new evolutionary search algorithm called Blackbox Gradient Sensing (BGS). We evaluate our method on a real world robotic table tennis setting, where the objective for the robot is to play cooperatively with a human player for as long as possible. Table tennis is a high-speed, dynamic task that requires the two players to react quickly to each other's moves, making for a challenging test bed for research on human-robot interaction. We present results on an industrial robotic arm that is able to cooperatively play table tennis with human players, achieving rallies of 22 successive hits on average and 150 at best. Further, for 80% of players, rally lengths are 70% to 175% longer compared to the sim-to-real plus fine-tuning (S2R+FT) baseline. For videos of our system in action, please see https://sites.google.com/view/is2r.

cs.RO↗

arXiv2025

Gaze-Guided Task Decomposition for Imitation Learning in Robotic Manipulation

In imitation learning for robotic manipulation, decomposing object manipulation tasks into sub-tasks enables the reuse of learned skills and the combination of learned behaviors to perform novel tasks, rather than simply replicating demonstrated motions. Human gaze is closely linked to hand movements during object manipulation. We hypothesize that an imitating agent's gaze control, fixating on specific landmarks and transitioning between them, simultaneously segments demonstrated manipulations into sub-tasks. This study proposes a simple yet robust task decomposition method based on gaze transitions. Using teleoperation, a common modality in robotic manipulation for collecting demonstrations, in which a human operator's gaze is measured and used for task decomposition as a substitute for an imitating agent's gaze. Our approach ensures consistent task decomposition across all demonstrations for each task, which is desirable in contexts such as machine learning. We evaluated the method across demonstrations of various tasks, assessing the characteristics and consistency of the resulting sub-tasks. Furthermore, extensive testing across different hyperparameter settings confirmed its robustness, making it adaptable to diverse robotic systems. Our code is available at https://github.com/crumbyRobotics/GazeTaskDecomp.

cs.RO↗

arXiv2025

MP1: MeanFlow Tames Policy Learning in 1-step for Robotic Manipulation

In robot manipulation, robot learning has become a prevailing approach. However, generative models within this field face a fundamental trade-off between the slow, iterative sampling of diffusion models and the architectural constraints of faster Flow-based methods, which often rely on explicit consistency losses. To address these limitations, we introduce MP1, which pairs 3D point-cloud inputs with the MeanFlow paradigm to generate action trajectories in one network function evaluation (1-NFE). By directly learning the interval-averaged velocity via the "MeanFlow Identity", our policy avoids any additional consistency constraints. This formulation eliminates numerical ODE-solver errors during inference, yielding more precise trajectories. MP1 further incorporates CFG for improved trajectory controllability while retaining 1-NFE inference without reintroducing structural constraints. Because subtle scene-context variations are critical for robot learning, especially in few-shot learning, we introduce a lightweight Dispersive Loss that repels state embeddings during training, boosting generalization without slowing inference. We validate our method on the Adroit and Meta-World benchmarks, as well as in real-world scenarios. Experimental results show MP1 achieves superior average task success rates, outperforming DP3 by 10.2% and FlowPolicy by 7.3%. Its average inference time is only 6.8 ms-19x faster than DP3 and nearly 2x faster than FlowPolicy. Our project page is available at https://mp1-2254.github.io/, and the code can be accessed at https://github.com/LogSSim/MP1.

cs.RO↗

arXiv2026

Improving Robotic Imitation Learning via Trajectory Standardization

Imitation learning for robotic manipulation relies on large sets of human demonstration trajectories, which are often noisy and temporally irregular due to variable operator speed, intermittent pauses, and inconsistent action density. A common preprocessing strategy is time-uniform downsampling to shorten sequences, but it cannot effectively remove speed-induced non-uniformity or redundant pauses. This mismatch degrades data quality and hinders policy learning. To address this issue, we propose Information-Standardized Trajectory Resampling (ISR), an offline preprocessing method for effective imitation learning. ISR resamples each trajectory by enforcing approximately equal information distance between adjacent points. Specifically, we map trajectories onto an information-modulated Riemannian manifold and perform geodesic-equidistant parameterization. We construct an information-intensity field from velocity and acceleration norms: the velocity term removes small-motion redundancy, while the acceleration term preserves high-curvature and fine-manipulation phases. We evaluate ISR on three real-world manipulation tasks with mainstream imitation learning policies. Compared with the baseline time-uniform 3x downsampling, ISR improves task success rates by about 25%, remains robust across datasets collected from different operators, and reduces both dataset size and training cost. The code and videos are publicly available at https://d-robotics-ai-lab.github.io/isr.page.

cs.RO↗

arXiv2019

Improving Data Efficiency of Self-supervised Learning for Robotic Grasping

Given the task of learning robotic grasping solely based on a depth camera input and gripper force feedback, we derive a learning algorithm from an applied point of view to significantly reduce the amount of required training data. Major improvements in time and data efficiency are achieved by: Firstly, we exploit the geometric consistency between the undistorted depth images and the task space. Using a relative small, fully-convolutional neural network, we predict grasp and gripper parameters with great advantages in training as well as inference performance. Secondly, motivated by the small random grasp success rate of around 3%, the grasp space was explored in a systematic manner. The final system was learned with 23000 grasp attempts in around 60h, improving current solutions by an order of magnitude. For typical bin picking scenarios, we measured a grasp success rate of 96.6%. Further experiments showed that the system is able to generalize and transfer knowledge to novel objects and environments.

cs.RO↗

arXiv2026

LAR-MoE: Latent-Aligned Routing for Mixture of Experts in Robotic Imitation Learning

Imitation learning enables robots to acquire manipulation skills from demonstrations, yet deploying a policy across tasks with heterogeneous dynamics remains challenging, as models tend to average over distinct behavioral modes present in the demonstrations. Mixture-of-Experts (MoE) architectures address this by activating specialized subnetworks, but requires meaningful skill decompositions for expert routing. We introduce Latent-Aligned Routing for Mixture of Experts (LAR-MoE), a two-stage framework that decouples unsupervised skill discovery from policy learning. In pre-training, we learn a joint latent representation between observations and future actions through student-teacher co-training. In a post-training stage, the expert routing is regularized to follow the structure of the learned latent space, preventing expert collapse while maintaining parameter efficiency. We evaluate LAR-MoE in simulation and on hardware. On the LIBERO benchmark, our method achieves a 95.2% average success rate with 150M parameters. On a surgical bowel grasping and retraction task, LAR-MoE matches a supervised MoE baseline without requiring any phase annotations, and transfers zero-shot to ex vivo porcine tissue. Our findings suggest that latent-aligned routing provides a principled alternative to supervised skill decomposition, enabling structured expert specialization from unlabeled demonstrations.

cs.RO↗

arXiv2020

Unsupervised Learning of Audio Perception for Robotics Applications: Learning to Project Data to T-SNE/UMAP space

Audio perception is a key to solving a variety of problems ranging from acoustic scene analysis, music meta-data extraction, recommendation, synthesis and analysis. It can potentially also augment computers in doing tasks that humans do effortlessly in day-to-day activities. This paper builds upon key ideas to build perception of touch sounds without access to any ground-truth data. We show how we can leverage ideas from classical signal processing to get large amounts of data of any sound of interest with a high precision. These sounds are then used, along with the images to map the sounds to a clustered space of the latent representation of these images. This approach, not only allows us to learn semantic representation of the possible sounds of interest, but also allows association of different modalities to the learned distinctions. The model trained to map sounds to this clustered representation, gives reasonable performance as opposed to expensive methods collecting a lot of human annotated data. Such approaches can be used to build a state of art perceptual model for any sound of interest described using a few signal processing features. Daisy chaining high precision sound event detectors using signal processing combined with neural architectures and high dimensional clustering of unlabelled data is a vastly powerful idea, and can be explored in a variety of ways in future.

cs.SD↗

arXiv2022

Grounding Hindsight Instructions in Multi-Goal Reinforcement Learning for Robotics

This paper focuses on robotic reinforcement learning with sparse rewards for natural language goal representations. An open problem is the sample-inefficiency that stems from the compositionality of natural language, and from the grounding of language in sensory data and actions. We address these issues with three contributions. We first present a mechanism for hindsight instruction replay utilizing expert feedback. Second, we propose a seq2seq model to generate linguistic hindsight instructions. Finally, we present a novel class of language-focused learning tasks. We show that hindsight instructions improve the learning performance, as expected. In addition, we also provide an unexpected result: We show that the learning performance of our agent can be improved by one third if, in a sense, the agent learns to talk to itself in a self-supervised manner. We achieve this by learning to generate linguistic instructions that would have been appropriate as a natural language goal for an originally unintended behavior. Our results indicate that the performance gain increases with the task-complexity.

cs.LG↗

arXiv2025

Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution

Reinforcement Learning (RL) robot controllers usually aggregate many task objectives into one scalar reward. While large-scale proximal policy optimisation (PPO) has enabled impressive results such as robust robot locomotion in the real world, many tasks still require careful reward tuning and are brittle to local optima. Tuning cost and sub-optimality grow with the number of objectives, limiting scalability. Modelling reward vectors and their trade-offs can address these issues; however, multi-objective methods remain underused in RL for robotics because of computational cost and optimisation difficulty. In this work, we investigate the conflict between gradient contributions for each objective that emerge from scalarising the task objectives. In particular, we explicitly address the conflict between task-based rewards and terms that regularise the policy towards realistic behaviour. We propose GCR-PPO, a modification to actor-critic optimisation that decomposes the actor update into objective-wise gradients using a multi-headed critic and resolves conflicts based on the objective priority. Our methodology, GCR-PPO, is evaluated on the well-known IsaacLab manipulation and locomotion benchmarks and additional multi-objective modifications on two related tasks. We show superior scalability compared to parallel PPO (p = 0.04), without significant computational overhead. We also show higher performance with more conflicting tasks. GCR-PPO improves on large-scale PPO with an average improvement of 9.5%, with high-conflict tasks observing a greater improvement. The code is available at https://github.com/humphreymunn/GCR-PPO.

cs.RO↗

arXiv2026

Contact Trajectory Prompting: In-Context Transfer of Contact-Rich Behaviors from a Single Demonstration

In-context robot learning enables robots to acquire new behaviors from demonstrations without test-time parameter updates. However, visual and kinematic specifications alone may not distinguish contact-rich behaviors that share similar motions but require different interaction intensities or patterns. We propose Contact Trajectory Prompting (CTP), a framework for one-shot transfer of contact-rich manipulation behaviors. CTP encodes motion and contact information from a single demonstration into an ordered contact trajectory prompt that captures their temporal evolution and specifies the desired physical interaction behavior. During execution, the policy uses online sensory feedback to retrieve interaction-relevant information from the prompt, conditioning closed-loop action generation on the demonstrated contact behavior. Across real-world wiping, rotation, and insertion tasks on objects excluded from training, CTP achieves 78.7% overall success, outperforming the strongest evaluated baseline by 13.0 percentage points. Changing only the reference demonstration enables CTP to follow contact specifications for both intensity and direction, including an intermediate wiping force level and clockwise or counterclockwise cap rotation. These results demonstrate that contact trajectories serve as effective behavioral specifications, extending in-context robot learning beyond motion imitation to physical interaction transfer. Project website: https://ctp-robotics.github.io/project_page.

cs.RO↗

arXiv2020

Autonomous Navigation with Mobile Robots using Deep Learning and the Robot Operating System

Autonomous navigation is a long-standing field of robotics research, which provides an essential capability for mobile robots to execute a series of tasks on the same environments performed by human everyday. In this chapter, we present a set of algorithms to train and deploy deep networks for autonomous navigation of mobile robots using the Robot Operation System (ROS). We describe three main steps to tackle this problem: i) collecting data in simulation environments using ROS and Gazebo; ii) designing deep network for autonomous navigation, and iii) deploying the learned policy on mobile robots in both simulation and real-world. Theoretically, we present deep learning architectures for robust navigation in normal environments (e.g., man-made houses, roads) and complex environments (e.g., collapsed cities, or natural caves). We further show that the use of visual modalities such as RGB, Lidar, and point cloud is essential to improve the autonomy of mobile robots. Our project website and demonstration video can be found at https://sites.google.com/site/autonomousnavigationros.

cs.RO↗

arXiv2022

Automatic Parameter Optimization Using Genetic Algorithm in Deep Reinforcement Learning for Robotic Manipulation Tasks

Learning agents can make use of Reinforcement Learning (RL) to decide their actions by using a reward function. However, the learning process is greatly influenced by the elect of values of the hyperparameters used in the learning algorithm. This work proposed a Deep Deterministic Policy Gradient (DDPG) and Hindsight Experience Replay (HER) based method, which makes use of the Genetic Algorithm (GA) to fine-tune the hyperparameters' values. This method (GA+DDPG+HER) experimented on six robotic manipulation tasks: FetchReach; FetchSlide; FetchPush; FetchPickAndPlace; DoorOpening; and AuboReach. Analysis of these results demonstrated a significant increase in performance and a decrease in learning time. Also, we compare and provide evidence that GA+DDPG+HER is better than the existing methods.

cs.RO↗