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 1,459 records · Page 81Linked to original sources

arXiv2024

Rank2Reward: Learning Shaped Reward Functions from Passive Video

Teaching robots novel skills with demonstrations via human-in-the-loop data collection techniques like kinesthetic teaching or teleoperation puts a heavy burden on human supervisors. In contrast to this paradigm, it is often significantly easier to provide raw, action-free visual data of tasks being performed. Moreover, this data can even be mined from video datasets or the web. Ideally, this data can serve to guide robot learning for new tasks in novel environments, informing both "what" to do and "how" to do it. A powerful way to encode both the "what" and the "how" is to infer a well-shaped reward function for reinforcement learning. The challenge is determining how to ground visual demonstration inputs into a well-shaped and informative reward function. We propose a technique Rank2Reward for learning behaviors from videos of tasks being performed without access to any low-level states and actions. We do so by leveraging the videos to learn a reward function that measures incremental "progress" through a task by learning how to temporally rank the video frames in a demonstration. By inferring an appropriate ranking, the reward function is able to guide reinforcement learning by indicating when task progress is being made. This ranking function can be integrated into an adversarial imitation learning scheme resulting in an algorithm that can learn behaviors without exploiting the learned reward function. We demonstrate the effectiveness of Rank2Reward at learning behaviors from raw video on a number of tabletop manipulation tasks in both simulations and on a real-world robotic arm. We also demonstrate how Rank2Reward can be easily extended to be applicable to web-scale video datasets.

cs.RO↗

arXiv2026

Adversarial Fine-tuning in Offline-to-Online Reinforcement Learning for Robust Robot Control

Offline reinforcement learning enables sample-efficient policy acquisition without risky online interaction, yet policies trained on static datasets remain brittle under action-space perturbations such as actuator faults. This study introduces an offline-to-online framework that trains policies on clean data and then performs adversarial fine-tuning, where perturbations are injected into executed actions to induce compensatory behavior and improve resilience. A performance-aware curriculum further adjusts the perturbation probability during training via an exponential-moving-average signal, balancing robustness and stability throughout the learning process. Experiments on continuous-control locomotion tasks demonstrate that the proposed method consistently improves robustness over offline-only baselines and converges faster than training from scratch. Matching the fine-tuning and evaluation conditions yields the strongest robustness to action-space perturbations, while the adaptive curriculum strategy mitigates the degradation of nominal performance observed with the linear curriculum strategy. Overall, the results show that adversarial fine-tuning enables adaptive and robust control under uncertain environments, bridging the gap between offline efficiency and online adaptability.

cs.RO↗

arXiv2026

ARCGym: Benchmarking Deep Reinforcement Learning in Autonomous Robotic Colonoscopy

Simulations for learning-based autonomous colonoscopic navigation focus mainly on fully actuated capsule robots, failing to capture the contact-rich navigation of long and flexible clinical colonoscopes. We present the Autonomous Robotic Colonoscopy Gym (ARCGym), an open-source reinforcement learning environment and benchmark for image-based navigation in clinically derived deformable colon anatomies. ARCGym supports multiple types of colonoscope robots, spanning capsule robots and flexible endoscopes, with this work focusing on flexible endoscopes including magnetic-driven tip actuation and clinically used proximally translational actuation. This work includes five CT-reconstructed colons representing typical clinical scenarios, a set of clinically meaningful navigation subtasks, and unified success metrics. We introduce a reward combining depth-based lumen alignment with a lumen-visibility score to improve learning under occlusions. Experiments across tasks, robots, and anatomies show that autonomous navigation remains challenging for both magnetic-driven and proximal-insertion flexible robots, with proximal-insertion actuation remaining an open problem.

cs.RO↗

arXiv2024

HumanoidBench: Simulated Humanoid Benchmark for Whole-Body Locomotion and Manipulation

Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology. However, research in humanoid robots is often bottlenecked by the costly and fragile hardware setups. To accelerate algorithmic research in humanoid robots, we present a high-dimensional, simulated robot learning benchmark, HumanoidBench, featuring a humanoid robot equipped with dexterous hands and a variety of challenging whole-body manipulation and locomotion tasks. Our findings reveal that state-of-the-art reinforcement learning algorithms struggle with most tasks, whereas a hierarchical learning approach achieves superior performance when supported by robust low-level policies, such as walking or reaching. With HumanoidBench, we provide the robotics community with a platform to identify the challenges arising when solving diverse tasks with humanoid robots, facilitating prompt verification of algorithms and ideas. The open-source code is available at https://humanoid-bench.github.io.

cs.RO↗

arXiv2023

Keyframe Demonstration Seeded and Bayesian Optimized Policy Search

This paper introduces a novel Learning from Demonstration framework to learn robotic skills with keyframe demonstrations using a Dynamic Bayesian Network (DBN) and a Bayesian Optimized Policy Search approach to improve the learned skills. DBN learns the robot motion, perceptual change in the object of interest (aka skill sub-goals) and the relation between them. The rewards are also learned from the perceptual part of the DBN. The policy search part is a semiblack box algorithm, which we call BO-PI2 . It utilizes the action-perception relation to focus the high-level exploration, uses Gaussian Processes to model the expected-return and performs Upper Confidence Bound type low-level exploration for sampling the rollouts. BO-PI2 is compared against a stateof-the-art method on three different skills in a real robot setting with expert and naive user demonstrations. The results show that our approach successfully focuses the exploration on the failed sub-goals and the addition of reward-predictive exploration outperforms the state-of-the-art approach on cumulative reward, skill success, and termination time metrics.

cs.RO↗

arXiv2018

Hierarchical Learning for Modular Robots

We argue that hierarchical methods can become the key for modular robots achieving reconfigurability. We present a hierarchical approach for modular robots that allows a robot to simultaneously learn multiple tasks. Our evaluation results present an environment composed of two different modular robot configurations, namely 3 degrees-of-freedom (DoF) and 4DoF with two corresponding targets. During the training, we switch between configurations and targets aiming to evaluate the possibility of training a neural network that is able to select appropriate motor primitives and robot configuration to achieve the target. The trained neural network is then transferred and executed on a real robot with 3DoF and 4DoF configurations. We demonstrate how this technique generalizes to robots with different configurations and tasks.

cs.RO↗

arXiv2012

Imitation learning of motor primitives and language bootstrapping in robots

Imitation learning in robots, also called programing by demonstration, has made important advances in recent years, allowing humans to teach context dependant motor skills/tasks to robots. We propose to extend the usual contexts investigated to also include acoustic linguistic expressions that might denote a given motor skill, and thus we target joint learning of the motor skills and their potential acoustic linguistic name. In addition to this, a modification of a class of existing algorithms within the imitation learning framework is made so that they can handle the unlabeled demonstration of several tasks/motor primitives without having to inform the imitator of what task is being demonstrated or what the number of tasks are, which is a necessity for language learning, i.e; if one wants to teach naturally an open number of new motor skills together with their acoustic names. Finally, a mechanism for detecting whether or not linguistic input is relevant to the task is also proposed, and our architecture also allows the robot to find the right framing for a given identified motor primitive. With these additions it becomes possible to build an imitator that bridges the gap between imitation learning and language learning by being able to learn linguistic expressions using methods from the imitation learning community. In this sense the imitator can learn a word by guessing whether a certain speech pattern present in the context means that a specific task is to be executed. The imitator is however not assumed to know that speech is relevant and has to figure this out on its own by looking at the demonstrations: indeed, the architecture allows the robot to transparently also learn tasks which should not be triggered by an acoustic word, but for example by the color or position of an object or a gesture made by someone in the environment. To demonstrate this ability to find the ...

cs.AI↗

arXiv2026

Learning From Failures: Efficient Reinforcement Learning Control with Episodic Memory

Reinforcement learning has achieved remarkable success in robot learning. However, under challenging exploration and contact-rich dynamics, early-stage training is frequently dominated by premature terminations such as collisions and falls. As a result, learning is overwhelmed by short-horizon, low-return trajectories, which hinder convergence and limit long-horizon exploration. To alleviate this issue, we propose a technique called Failure Episodic Memory Alert (FEMA). FEMA explicitly stores short-horizon failure experiences through an episodic memory module. During interactions, it retrieves similar failure experiences and prevents the robot from recurrently relapsing into unstable states, guiding the policy toward long-horizon trajectories with greater long-term value. FEMA can be combined easily with model-free reinforcement learning algorithms, and yields a substantial sample-efficiency improvement of 33.11% on MuJoCo tasks across several classical RL algorithms. Furthermore, integrating FEMA into a parallelized PPO training pipeline demonstrates its effectiveness on a real-world bipedal robot task.

cs.RO↗

arXiv2022

Causal Inference for De-biasing Motion Estimation from Robotic Observational Data

Robot data collected in complex real-world scenarios are often biased due to safety concerns, human preferences, and mission or platform constraints. Consequently, robot learning from such observational data poses great challenges for accurate parameter estimation. We propose a principled causal inference framework for robots to learn the parameters of a stochastic motion model using observational data. Specifically, we leverage the de-biasing functionality of the potential-outcome causal inference framework, the Inverse Propensity Weighting (IPW), and the Doubly Robust (DR) methods, to obtain a better parameter estimation of the robot's stochastic motion model. The IPW is a re-weighting approach to ensure unbiased estimation, and the DR approach further combines any two estimators to strengthen the unbiased result even if one of these estimators is biased. We then develop an approximate policy iteration algorithm using the bias-eliminated estimated state transition function. We validate our framework using both simulation and real-world experiments, and the results have revealed that the proposed causal inference-based navigation and control framework can correctly and efficiently learn the parameters from biased observational data.

cs.RO↗

arXiv2021

rl_reach: Reproducible Reinforcement Learning Experiments for Robotic Reaching Tasks

Training reinforcement learning agents at solving a given task is highly dependent on identifying optimal sets of hyperparameters and selecting suitable environment input / output configurations. This tedious process could be eased with a straightforward toolbox allowing its user to quickly compare different training parameter sets. We present rl_reach, a self-contained, open-source and easy-to-use software package designed to run reproducible reinforcement learning experiments for customisable robotic reaching tasks. rl_reach packs together training environments, agents, hyperparameter optimisation tools and policy evaluation scripts, allowing its users to quickly investigate and identify optimal training configurations. rl_reach is publicly available at this URL: https://github.com/PierreExeter/rl_reach.

cs.LG↗

arXiv2024

Toward a Surgeon-in-the-Loop Ophthalmic Robotic Apprentice using Reinforcement and Imitation Learning

Robot-assisted surgical systems have demonstrated significant potential in enhancing surgical precision and minimizing human errors. However, existing systems cannot accommodate individual surgeons' unique preferences and requirements. Additionally, they primarily focus on general surgeries (e.g., laparoscopy) and are unsuitable for highly precise microsurgeries, such as ophthalmic procedures. Thus, we propose an image-guided approach for surgeon-centered autonomous agents that can adapt to the individual surgeon's skill level and preferred surgical techniques during ophthalmic cataract surgery. Our approach trains reinforcement and imitation learning agents simultaneously using curriculum learning approaches guided by image data to perform all tasks of the incision phase of cataract surgery. By integrating the surgeon's actions and preferences into the training process, our approach enables the robot to implicitly learn and adapt to the individual surgeon's unique techniques through surgeon-in-the-loop demonstrations. This results in a more intuitive and personalized surgical experience for the surgeon while ensuring consistent performance for the autonomous robotic apprentice. We define and evaluate the effectiveness of our approach in a simulated environment using our proposed metrics and highlight the trade-off between a generic agent and a surgeon-centered adapted agent. Finally, our approach has the potential to extend to other ophthalmic and microsurgical procedures, opening the door to a new generation of surgeon-in-the-loop autonomous surgical robots. We provide an open-source simulation framework for future development and reproducibility at https://github.com/amrgomaaelhady/CataractAdaptSurgRobot.

cs.RO↗

arXiv2023

A Framework for Learning from Demonstration with Minimal Human Effort

We consider robot learning in the context of shared autonomy, where control of the system can switch between a human teleoperator and autonomous control. In this setting we address reinforcement learning, and learning from demonstration, where there is a cost associated with human time. This cost represents the human time required to teleoperate the robot, or recover the robot from failures. For each episode, the agent must choose between requesting human teleoperation, or using one of its autonomous controllers. In our approach, we learn to predict the success probability for each controller, given the initial state of an episode. This is used in a contextual multi-armed bandit algorithm to choose the controller for the episode. A controller is learnt online from demonstrations and reinforcement learning so that autonomous performance improves, and the system becomes less reliant on the teleoperator with more experience. We show that our approach to controller selection reduces the human cost to perform two simulated tasks and a single real-world task.

cs.LG↗

arXiv2021

Reinforcement Learning Approaches in Social Robotics

This article surveys reinforcement learning approaches in social robotics. Reinforcement learning is a framework for decision-making problems in which an agent interacts through trial-and-error with its environment to discover an optimal behavior. Since interaction is a key component in both reinforcement learning and social robotics, it can be a well-suited approach for real-world interactions with physically embodied social robots. The scope of the paper is focused particularly on studies that include social physical robots and real-world human-robot interactions with users. We present a thorough analysis of reinforcement learning approaches in social robotics. In addition to a survey, we categorize existent reinforcement learning approaches based on the used method and the design of the reward mechanisms. Moreover, since communication capability is a prominent feature of social robots, we discuss and group the papers based on the communication medium used for reward formulation. Considering the importance of designing the reward function, we also provide a categorization of the papers based on the nature of the reward. This categorization includes three major themes: interactive reinforcement learning, intrinsically motivated methods, and task performance-driven methods. The benefits and challenges of reinforcement learning in social robotics, evaluation methods of the papers regarding whether or not they use subjective and algorithmic measures, a discussion in the view of real-world reinforcement learning challenges and proposed solutions, the points that remain to be explored, including the approaches that have thus far received less attention is also given in the paper. Thus, this paper aims to become a starting point for researchers interested in using and applying reinforcement learning methods in this particular research field.

cs.RO↗

arXiv2019

Empathic Robot for Group Learning: A Field Study

This work explores a group learning scenario with an autonomous empathic robot. We address two research questions: (1) Can an autonomous robot designed with empathic competencies foster collaborative learning in a group context? (2) Can an empathic robot sustain positive educational outcomes in long-term collaborative learning interactions with groups of students? To answer these questions, we developed an autonomous robot with empathic competencies that is able to interact with a group of students in a learning activity about sustainable development. Two studies were conducted. The first study compares learning outcomes in children across 3 conditions: learning with an empathic robot; learning with a robot without empathic capabilities; and learning without a robot. The results show that the autonomous robot with empathy fosters meaningful discussions about sustainability, which is a learning outcome in sustainability education. The second study features groups of students who interact with the robot in a school classroom for two months. The long-term educational interaction did not seem to provide significant learning gains, although there was a change in game-actions to achieve more sustainability during game-play. This result reflects the need to perform more long-term research in the field of educational robots for group learning.

cs.HC↗

arXiv2025

Prolonging Tool Life: Learning Skillful Use of General-purpose Tools through Lifespan-guided Reinforcement Learning

In inaccessible environments with uncertain task demands, robots often rely on general-purpose tools that lack predefined usage strategies. These tools are not tailored for particular operations, making their longevity highly sensitive to how they are used. This creates a fundamental challenge: how can a robot learn a tool-use policy that both completes the task and prolongs the tool's lifespan? In this work, we address this challenge by introducing a reinforcement learning (RL) framework that incorporates tool lifespan as a factor during policy optimization. Our framework leverages Finite Element Analysis (FEA) and Miner's Rule to estimate Remaining Useful Life (RUL) based on accumulated stress, and integrates the RUL into the RL reward to guide policy learning toward lifespan-guided behavior. To handle the fact that RUL can only be estimated after task execution, we introduce an Adaptive Reward Normalization (ARN) mechanism that dynamically adjusts reward scaling based on estimated RULs, ensuring stable learning signals. We validate our method across simulated and real-world tool use tasks, including Object-Moving and Door-Opening with multiple general-purpose tools. The learned policies consistently prolong tool lifespan (up to 8.01x in simulation) and transfer effectively to real-world settings, demonstrating the practical value of learning lifespan-guided tool use strategies.

cs.RO↗

arXiv2017

Optimal and Learning Control for Autonomous Robots

Optimal and Learning Control for Autonomous Robots has been taught in the Robotics, Systems and Controls Masters at ETH Zurich with the aim to teach optimal control and reinforcement learning for closed loop control problems from a unified point of view. The starting point is the formulation of of an optimal control problem and deriving the different types of solutions and algorithms from there. These lecture notes aim at supporting this unified view with a unified notation wherever possible, and a bit of a translation help to compare the terminology and notation in the different fields. The course assumes basic knowledge of Control Theory, Linear Algebra and Stochastic Calculus.

eess.SY↗

arXiv2015

Object Structure from Manipulation via Particle Filter and Robot-based Active Learning

To learn object models for robotic manipulation, unsupervised methods cannot provide accurate object structural information and supervised methods require a large amount of manually labeled training samples, thus interactive object segmentation is developed to automate object modeling. In this article, we formulate a novel dynamic process for interactive object segmentation, and develop a solution based on particle filter and active learning so that a robot can manipulate and learn object structures incrementally and automatically. We demonstrate our method with a humanoidrobot on different types of objects, and compare its segmentation performancewith established methods on selected objects. The result shows that our approach allows more accurate object modeling and reveals richer object structural information.

cs.RO↗

arXiv2024

3D Diffuser Actor: Policy Diffusion with 3D Scene Representations

Diffusion policies are conditional diffusion models that learn robot action distributions conditioned on the robot and environment state. They have recently shown to outperform both deterministic and alternative action distribution learning formulations. 3D robot policies use 3D scene feature representations aggregated from a single or multiple camera views using sensed depth. They have shown to generalize better than their 2D counterparts across camera viewpoints. We unify these two lines of work and present 3D Diffuser Actor, a neural policy equipped with a novel 3D denoising transformer that fuses information from the 3D visual scene, a language instruction and proprioception to predict the noise in noised 3D robot pose trajectories. 3D Diffuser Actor sets a new state-of-the-art on RLBench with an absolute performance gain of 18.1% over the current SOTA on a multi-view setup and an absolute gain of 13.1% on a single-view setup. On the CALVIN benchmark, it improves over the current SOTA by a 9% relative increase. It also learns to control a robot manipulator in the real world from a handful of demonstrations. Through thorough comparisons with the current SOTA policies and ablations of our model, we show 3D Diffuser Actor's design choices dramatically outperform 2D representations, regression and classification objectives, absolute attentions, and holistic non-tokenized 3D scene embeddings.

cs.RO↗