Search arXiv⌕ Search

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 1,027 records · Page 57Linked to original sources
arXiv2026

Robots that learn to evaluate models of collective behavior

Understanding and modeling animal behavior is essential for studying collective motion, decision-making, and bio-inspired robotics. Yet, evaluating the accuracy of behavioral models still often relies on offline comparisons to static trajectory statistics. Here we introduce a reinforcement-learning-based framework that uses a biomimetic robotic fish (RoboFish) to evaluate computational models of live fish behavior through closed-loop interaction. We trained policies in simulation using four distinct fish models-a simple constant-follow baseline, two rule-based models, and a biologically grounded convolutional neural network model-and transferred these policies to the real RoboFish setup, where they interacted with live fish. Policies were trained to guide a simulated fish to goal locations, enabling us to quantify how the response of real fish differs from the simulated fish's response. We evaluate the fish models by quantifying the sim-to-real gaps, defined as the Wasserstein distance between simulated and real distributions of behavioral metrics such as goal-reaching performance, inter-individual distances, wall interactions, and alignment. The neural network-based fish model exhibited the smallest gap across goal-reaching performance and most other metrics, indicating higher behavioral fidelity than conventional rule-based models under this benchmark. More importantly, this separation shows that the proposed evaluation can quantitatively distinguish candidate models under matched closed-loop conditions. Our work demonstrates how learning-based robotic experiments can uncover deficiencies in behavioral models and provides a general framework for evaluating animal behavior models through embodied interaction.

cs.RO↗
arXiv2023

RobotGPT: Robot Manipulation Learning from ChatGPT

We present RobotGPT, an innovative decision framework for robotic manipulation that prioritizes stability and safety. The execution code generated by ChatGPT cannot guarantee the stability and safety of the system. ChatGPT may provide different answers for the same task, leading to unpredictability. This instability prevents the direct integration of ChatGPT into the robot manipulation loop. Although setting the temperature to 0 can generate more consistent outputs, it may cause ChatGPT to lose diversity and creativity. Our objective is to leverage ChatGPT's problem-solving capabilities in robot manipulation and train a reliable agent. The framework includes an effective prompt structure and a robust learning model. Additionally, we introduce a metric for measuring task difficulty to evaluate ChatGPT's performance in robot manipulation. Furthermore, we evaluate RobotGPT in both simulation and real-world environments. Compared to directly using ChatGPT to generate code, our framework significantly improves task success rates, with an average increase from 38.5% to 91.5%. Therefore, training a RobotGPT by utilizing ChatGPT as an expert is a more stable approach compared to directly using ChatGPT as a task planner.

cs.RO↗
arXiv2019

Cascaded Gaussian Processes for Data-efficient Robot Dynamics Learning

Motivated by the recursive Newton-Euler formulation, we propose a novel cascaded Gaussian process learning framework for the inverse dynamics of robot manipulators. This approach leads to a significant dimensionality reduction which in turn results in better learning and data efficiency. We explore two formulations for the cascading: the inward and outward, both along the manipulator chain topology. The learned modeling is tested in conjunction with the classical inverse dynamics model (semi-parametric) and on its own (non-parametric) in the context of feed-forward control of the arm. Experimental results are obtained with Jaco 2 six-DOF and SARCOS seven-DOF manipulators for randomly defined sinusoidal motions of the joints in order to evaluate the performance of cascading against the standard GP learning. In addition, experiments are conducted using Jaco 2 on a task emulating a pouring maneuver. Results indicate a consistent improvement in learning speed with the inward cascaded GP model and an overall improvement in data efficiency and generalization.

cs.RO↗
arXiv2021

Uncertainty-aware deep learning for robot touch: Application to Bayesian tactile servo control

This work investigates uncertainty-aware deep learning (DL) in tactile robotics based on a general framework introduced recently for robot vision. For a test scenario, we consider optical tactile sensing in combination with DL to estimate the edge pose as a feedback signal to servo around various 2D test objects. We demonstrate that uncertainty-aware DL can improve the pose estimation over deterministic DL methods. The system estimates the uncertainty associated with each prediction, which is used along with temporal coherency to improve the predictions via a Kalman filter, and hence improve the tactile servo control. The robot is able to robustly follow all of the presented contour shapes to reduce not only the error by a factor of two but also smooth the trajectory from the undesired noisy behaviour caused by previous deterministic networks. In our view, as the field of tactile robotics matures in its use of DL, the estimation of uncertainty will become a key component in the control of physically interactive tasks in complex environments.

cs.RO↗
arXiv2022

Dependability Analysis of Deep Reinforcement Learning based Robotics and Autonomous Systems through Probabilistic Model Checking

While Deep Reinforcement Learning (DRL) provides transformational capabilities to the control of Robotics and Autonomous Systems (RAS), the black-box nature of DRL and uncertain deployment environments of RAS pose new challenges on its dependability. Although existing works impose constraints on the DRL policy to ensure successful completion of the mission, it is far from adequate to assess the DRL-driven RAS in a holistic way considering all dependability properties. In this paper, we formally define a set of dependability properties in temporal logic and construct a Discrete-Time Markov Chain (DTMC) to model the dynamics of risk/failures of a DRL-driven RAS interacting with the stochastic environment. We then conduct Probabilistic Model Checking (PMC) on the designed DTMC to verify those properties. Our experimental results show that the proposed method is effective as a holistic assessment framework while uncovering conflicts between the properties that may need trade-offs in training. Moreover, we find that the standard DRL training cannot improve dependability properties, thus requiring bespoke optimisation objectives. Finally, our method offers sensitivity analysis of dependability properties to disturbance levels from environments, providing insights for the assurance of real RAS.

cs.RO↗
arXiv2022

Learning Stable Robotic Skills on Riemannian Manifolds

In this paper, we propose an approach to learn stable dynamical systems evolving on Riemannian manifolds. The approach leverages a data-efficient procedure to learn a diffeomorphic transformation that maps simple stable dynamical systems onto complex robotic skills. By exploiting mathematical tools from differential geometry, the method ensures that the learned skills fulfill the geometric constraints imposed by the underlying manifolds, such as unit quaternion (UQ) for orientation and symmetric positive definite (SPD) matrices for impedance, while preserving the convergence to a given target. The proposed approach is firstly tested in simulation on a public benchmark, obtained by projecting Cartesian data into UQ and SPD manifolds, and compared with existing approaches. Apart from evaluating the approach on a public benchmark, several experiments were performed on a real robot performing bottle stacking in different conditions and a drilling task in cooperation with a human operator. The evaluation shows promising results in terms of learning accuracy and task adaptation capabilities.

cs.RO↗
arXiv2026

World4RL: Diffusion World Models for Policy Refinement with Reinforcement Learning for Robotic Manipulation

Robotic manipulation policies are commonly initialized through imitation learning, but their performance is limited by the scarcity and narrow coverage of expert data. Reinforcement learning can refine polices to alleviate this limitation, yet real-robot training is costly and unsafe, while training in simulators suffers from the sim-to-real gap. Recent advances in generative models have demonstrated remarkable capabilities in real-world simulation, with diffusion models in particular excelling at generation. This raises the question of how diffusion model-based world models can be combined to enhance pre-trained policies in robotic manipulation. In this work, we propose World4RL, a framework that employs diffusion-based world models as high-fidelity simulators to refine pre-trained policies entirely in imagined environments for robotic manipulation. Unlike prior works that primarily employ world models for planning, our framework enables direct end-to-end policy optimization. World4RL is designed around two principles: pre-training a diffusion world model that captures diverse dynamics on multi-task datasets and refining policies entirely within a frozen world model to avoid online real-world interactions. We further design a two-hot action encoding scheme tailored for robotic manipulation and adopt diffusion backbones to improve modeling fidelity. Extensive simulation and real-world experiments demonstrate that World4RL provides high-fidelity environment modeling and enables consistent policy refinement, yielding significantly higher success rates compared to imitation learning and other baselines.

cs.RO↗
arXiv2023

Stylized Table Tennis Robots Skill Learning with Incomplete Human Demonstrations

In recent years, Reinforcement Learning (RL) is becoming a popular technique for training controllers for robots. However, for complex dynamic robot control tasks, RL-based method often produces controllers with unrealistic styles. In contrast, humans can learn well-stylized skills under supervisions. For example, people learn table tennis skills by imitating the motions of coaches. Such reference motions are often incomplete, e.g. without the presence of an actual ball. Inspired by this, we propose an RL-based algorithm to train a robot that can learn the playing style from such incomplete human demonstrations. We collect data through the teaching-and-dragging method. We also propose data augmentation techniques to enable our robot to adapt to balls of different velocities. We finally evaluate our policy in different simulators with varying dynamics.

cs.RO↗
arXiv2018

What Can This Robot Do? Learning from Appearance and Experiments

When presented with an unknown robot (subject) how can an autonomous agent (learner) figure out what this new robot can do? The subject's appearance can provide cues to its physical as well as cognitive capabilities. Seeing a humanoid can make one wonder if it can kick balls, climb stairs or recognize faces. What if the learner can request the subject to perform these tasks? We present an approach to make the learner build a model of the subject at a task based on the latter's appearance and refine it by experimentation. Apart from the subject's inherent capabilities, certain extrinsic factors may affect its performance at a task. Based on the subject's appearance and prior knowledge about the task a learner can identify a set of potential factors, a subset of which we assume are controllable. Our approach picks values of controllable factors to generate the most informative experiments to test the subject at. Additionally, we present a metric to determine if a factor should be incorporated in the model. We present results of our approach on modeling a humanoid robot at the task of kicking a ball. Firstly, we show that actively picking values for controllable factors, even in noisy experiments, leads to faster learning of the subject's model for the task. Secondly, starting from a minimal set of factors our metric identifies the set of relevant factors to incorporate in the model. Lastly, we show that the refined model better represents the subject's performance at the task.

cs.AI↗
arXiv2026

Simultaneous Tactile-Visual Perception for Learning Multimodal Robot Manipulation

Robotic manipulation requires both rich multimodal perception and effective learning frameworks to handle complex real-world tasks. See-through-skin (STS) sensors, which combine tactile and visual perception, offer promising sensing capabilities, while modern imitation learning provides powerful tools for policy acquisition. However, existing STS designs lack simultaneous multimodal perception and suffer from unreliable tactile tracking. Furthermore, integrating these rich multimodal signals into learning-based manipulation pipelines remains an open challenge. We introduce TacThru, an STS sensor enabling simultaneous visual perception and robust tactile signal extraction, and TacThru-UMI, an imitation learning framework that leverages these multimodal signals for manipulation. Our sensor features a fully transparent elastomer, persistent illumination, novel keyline markers, and efficient tracking, while our learning system integrates these signals through a Transformer-based Diffusion Policy. Experiments on five challenging real-world tasks show that TacThru-UMI achieves an average success rate of 85.5%, significantly outperforming the baselines of tactile policy(66.3%) and vision-only policy (55.4%). The system excels in critical scenarios, including contact detection with thin and soft objects and precision manipulation requiring multimodal coordination. This work demonstrates that combining simultaneous multimodal perception with modern learning frameworks enables more precise, adaptable robotic manipulation.

cs.RO↗
arXiv2022

GA+DDPG+HER: Genetic Algorithm-Based Function Optimizer in Deep Reinforcement Learning for Robotic Manipulation Tasks

Agents can base decisions made using reinforcement learning (RL) on a reward function. The selection of values for the learning algorithm parameters can, nevertheless, have a substantial impact on the overall learning process. In order to discover values for the learning parameters that are close to optimal, we extended our previously proposed genetic algorithm-based Deep Deterministic Policy Gradient and Hindsight Experience Replay approach (referred to as GA+DDPG+HER) in this study. On the robotic manipulation tasks of FetchReach, FetchSlide, FetchPush, FetchPick&Place, and DoorOpening, we applied the GA+DDPG+HER methodology. Our technique GA+DDPG+HER was also used in the AuboReach environment with a few adjustments. Our experimental analysis demonstrates that our method produces performance that is noticeably better and occurs faster than the original algorithm. We also offer proof that GA+DDPG+HER beat the current approaches. The final results support our assertion and offer sufficient proof that automating the parameter tuning procedure is crucial and does cut down learning time by as much as 57%.

cs.RO↗
arXiv2020

Investigating the Effects of Robot Engagement Communication on Learning from Demonstration

Robot Learning from Demonstration (RLfD) is a technique for robots to derive policies from instructors' examples. Although the reciprocal effects of student engagement on teacher behavior are widely recognized in the educational community, it is unclear whether the same phenomenon holds true for RLfD. To fill this gap, we first design three types of robot engagement behavior (attention, imitation, and a hybrid of the two) based on the learning literature. We then conduct, in a simulation environment, a within-subject user study to investigate the impact of different robot engagement cues on humans compared to a "without-engagement" condition. Results suggest that engagement communication significantly changes the human's estimation of the robots' capability and significantly raises their expectation towards the learning outcomes, even though we do not run actual learning algorithms in the experiments. Moreover, imitation behavior affects humans more than attention does in all metrics, while their combination has the most profound influences on humans. We also find that communicating engagement via imitation or the combined behavior significantly improve humans' perception towards the quality of demonstrations, even if all demonstrations are of the same quality.

cs.HC↗
arXiv2022

Learning for Robot Decision Making under Distribution Shift: A Survey

With the recent advances in the field of deep learning, learning-based methods are widely being implemented in various robotic systems that help robots understand their environment and make informed decisions to achieve a wide variety of tasks or goals. However, learning-based methods have repeatedly been shown to have poor generalization when they are presented with inputs that are different from those during training leading to the problem of distribution shift. Any robotic system that employs learning-based methods is prone to distribution shift which might lead the agents to make decisions that lead to degraded performance or even catastrophic failure. In this paper, we discuss various techniques that have been proposed in the literature to aid or improve decision making under distribution shift for robotic systems. We present a taxonomy of existing literature and present a survey of existing approaches in the area based on this taxonomy. Finally, we also identify a few open problems in the area that could serve as future directions for research.

cs.RO↗
arXiv2018

Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards

We propose a general and model-free approach for Reinforcement Learning (RL) on real robotics with sparse rewards. We build upon the Deep Deterministic Policy Gradient (DDPG) algorithm to use demonstrations. Both demonstrations and actual interactions are used to fill a replay buffer and the sampling ratio between demonstrations and transitions is automatically tuned via a prioritized replay mechanism. Typically, carefully engineered shaping rewards are required to enable the agents to efficiently explore on high dimensional control problems such as robotics. They are also required for model-based acceleration methods relying on local solvers such as iLQG (e.g. Guided Policy Search and Normalized Advantage Function). The demonstrations replace the need for carefully engineered rewards, and reduce the exploration problem encountered by classical RL approaches in these domains. Demonstrations are collected by a robot kinesthetically force-controlled by a human demonstrator. Results on four simulated insertion tasks show that DDPG from demonstrations out-performs DDPG, and does not require engineered rewards. Finally, we demonstrate the method on a real robotics task consisting of inserting a clip (flexible object) into a rigid object.

cs.AI↗
arXiv2024

Planning the path with Reinforcement Learning: Optimal Robot Motion Planning in RoboCup Small Size League Environments

This work investigates the potential of Reinforcement Learning (RL) to tackle robot motion planning challenges in the dynamic RoboCup Small Size League (SSL). Using a heuristic control approach, we evaluate RL's effectiveness in obstacle-free and single-obstacle path-planning environments. Ablation studies reveal significant performance improvements. Our method achieved a 60% time gain in obstacle-free environments compared to baseline algorithms. Additionally, our findings demonstrated dynamic obstacle avoidance capabilities, adeptly navigating around moving blocks. These findings highlight the potential of RL to enhance robot motion planning in the challenging and unpredictable SSL environment.

cs.RO↗
arXiv2021

The Holy Grail of Multi-Robot Planning: Learning to Generate Online-Scalable Solutions from Offline-Optimal Experts

Many multi-robot planning problems are burdened by the curse of dimensionality, which compounds the difficulty of applying solutions to large-scale problem instances. The use of learning-based methods in multi-robot planning holds great promise as it enables us to offload the online computational burden of expensive, yet optimal solvers, to an offline learning procedure. Simply put, the idea is to train a policy to copy an optimal pattern generated by a small-scale system, and then transfer that policy to much larger systems, in the hope that the learned strategy scales, while maintaining near-optimal performance. Yet, a number of issues impede us from leveraging this idea to its full potential. This blue-sky paper elaborates some of the key challenges that remain.

cs.RO↗
arXiv2026

Physical Atari: A Robust and Accessible Platform for Real-time Reinforcement Learning on Robots

We built a robot called the Robotroller that actuates an Atari CX40+ controller and a device called the Atari Devbox that renders the game frame and the reward signal from the Arcade Learning Environment on a screen. The Robotroller and the Atari Devbox, together with an off-the-shelf camera and a desktop computer, constitute a system that can be used to study reinforcement learning algorithms in the physical world. We call the full system Physical Atari. In this paper, we detail the key decisions that make Physical Atari a robust and accessible platform. To make the system robust, we designed the Robotroller so that all movement is done through bearings, which reduces wear. Additionally, we wrote software that monitors the state of the servos at a high frequency and intervenes to limit stress. To make the system accessible, we used affordable off-the-shelf components and parts that can be manufactured using consumer 3D printers. Physical Atari can be built for under $1,000 and has been used for weeks of non-stop reinforcement learning experiments without any mechanical failures. We used it to validate that reinforcement learning algorithms can learn directly on robots and show that even small distribution shifts between learning and deployment can significantly degrade the performance of policies. Our results underscore the importance of on-device adaptation for strong performance on robots.

cs.RO↗