Suchergebnisse - Deep learning in robotics and automation

Deep Learning Approaches to Grasp Synthesis: A Review von Newbury, Rhys, Gu, Morris, Chumbley, Lachlan, Mousavian, Arsalan, Eppner, Clemens, Leitner, Jurgen, Bohg, Jeannette, Morales, Antonio, Asfour, Tamim, Kragic, Danica, Fox, Dieter, Cosgun, Akansel

“… Recent advances in deep learning methods have allowed rapid progress in robotic object grasping …”
Volltext

Safe Control With Learned Certificates: A Survey of Neural Lyapunov, Barrier, and Contraction Methods for Robotics and Control von Dawson, Charles, Gao, Sicun, Fan, Chuchu

“… Learning-enabled control systems have demonstrated impressive empirical performance on challenging control problems in robotics, but this performance comes at the cost of reduced transparency and lack …”
Volltext

Cat-Like Jumping and Landing of Legged Robots in Low Gravity Using Deep Reinforcement Learning von Rudin, Nikita, Kolvenbach, Hendrik, Tsounis, Vassilios, Hutter, Marco

“… Using an off-the-shelf deep reinforcement learning algorithm, we train a neural network to control a jumping quadruped robot while solely using its limbs for attitude control …”
Volltext

Flow: A Modular Learning Framework for Mixed Autonomy Traffic von Wu, Cathy, Kreidieh, Abdul Rahman, Parvate, Kanaad, Vinitsky, Eugene, Bayen, Alexandre M.

“… To shed light into near-term AV impacts, this article studies the suitability of deep reinforcement learning (RL …”
Volltext

DRL-VO: Learning to Navigate Through Crowded Dynamic Scenes Using Velocity Obstacles von Xie, Zhanteng, Dames, Philip

“… This article proposes a novel learning-based control policy with strong generalizability to new environments that enables a mobile robot to navigate autonomously through spaces filled with both static …”
Volltext

Towards Generalization in Target-Driven Visual Navigation by Using Deep Reinforcement Learning von Devo, Alessandro, Mezzetti, Giacomo, Costante, Gabriele, Fravolini, Mario L., Valigi, Paolo

“… Recent fruitful approaches rely on deep reinforcement learning, which has proven to be an effective framework to learn navigation policies …”
Volltext

Motion Planning Networks: Bridging the Gap Between Learning-Based and Classical Motion Planners von Qureshi, Ahmed Hussain, Miao, Yinglong, Simeonov, Anthony, Yip, Michael C.

“… This article describes motion planning networks (MPNet), a computationally efficient, learning-based neural planner for solving motion planning …”
Volltext

A General Framework for Uncertainty Estimation in Deep Learning von Loquercio, Antonio, Segu, Mattia, Scaramuzza, Davide

“… Being able to detect such failures automatically is fundamental to integrate deep learning algorithms into robotics …”
Volltext

RLOC: Terrain-Aware Legged Locomotion Using Reinforcement Learning and Optimal Control von Gangapurwala, Siddhant, Geisert, Mathieu, Orsolino, Romeo, Fallon, Maurice, Havoutis, Ioannis

“… We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired base velocity commands into footstep plans using a reinforcement learning (RL) policy …”
Volltext

Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks von Lee, Michelle A., Zhu, Yuke, Zachares, Peter, Tan, Matthew, Srinivasan, Krishnan, Savarese, Silvio, Fei-Fei, Li, Garg, Animesh, Bohg, Jeannette

“… While deep reinforcement learning has shown success in learning control policies for high-dimensional inputs, these algorithms are generally intractable to train directly on real robots due to sample complexity …”
Volltext

Unsupervised Deep Homography: A Fast and Robust Homography Estimation Model von Ty Nguyen, Chen, Steven W., Shivakumar, Shreyas S., Taylor, Camillo Jose, Kumar, Vijay

“… The usage on a robotic system requires a fast and robust homography estimation algorithm. In this letter, we propose an unsupervised learning algorithm that trains a deep convolutional neural network to estimate planar homographies …”
Volltext

Object Detection Using Sim2Real Domain Randomization for Robotic Applications von Horvath, Daniel, Erdos, Gabor, Istenes, Zoltan, Horvath, Tomas, Foldi, Sandor

“… One of the main obstacles of deep-learning-based models in the field of robotics is the lack of domain-specific labeled data for different industrial applications …”
Volltext

Deep Neural Network Based Electrical Impedance Tomographic Sensing Methodology for Large-Area Robotic Tactile Sensing von Park, Hyunkyu, Park, Kyungseo, Mo, Sangwoo, Kim, Jung

“… , but the degradation of a tactile spatial resolution has remained challenging. This article describes a deep neural network based EIT reconstruction framework, the EIT neural network (EIT-NN …”
Volltext

RLBench: The Robot Learning Benchmark & Learning Environment von James, Stephen, Ma, Zicong, Arrojo, David Rovick, Davison, Andrew J.

“… We present a challenging new benchmark and learning-environment for robot learning …”
Volltext

Deep Reinforcement Learning Robot for Search and Rescue Applications: Exploration in Unknown Cluttered Environments von Niroui, Farzad, Kaicheng Zhang, Kashino, Zendai, Nejat, Goldie

“… Due to the unpredictable nature of these environments, deep learning techniques can be used to perform these tasks …”
Volltext

More Than a Feeling: Learning to Grasp and Regrasp Using Vision and Touch von Calandra, Roberto, Owens, Andrew, Jayaraman, Dinesh, Lin, Justin, Wenzhen Yuan, Malik, Jitendra, Adelson, Edward H., Levine, Sergey

“… Most recent robotic grasping work, however, has been based only on visual input, and thus cannot easily benefit from feedback after initiating contact …”
Volltext

DeepGait: Planning and Control of Quadrupedal Gaits Using Deep Reinforcement Learning von Tsounis, Vassilios, Alge, Mitja, Lee, Joonho, Farshidian, Farbod, Hutter, Marco

“… In this work, we propose a novel technique for training neural-network policies for terrain-aware locomotion, which combines state-of-the-art methods for model-based motion planning and reinforcement learning …”
Volltext

Fast Underwater Image Enhancement for Improved Visual Perception von Islam, Md Jahidul, Xia, Youya, Sattar, Junaed

“… In this letter, we present a conditional generative adversarial network-based model for real-time underwater image enhancement. To supervise the adversarial …”
Volltext

DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor With Application to In-Hand Manipulation von Lambeta, Mike, Chou, Po-Wei, Tian, Stephen, Yang, Brian, Maloon, Benjamin, Most, Victoria Rose, Stroud, Dave, Santos, Raymond, Byagowi, Ahmad, Kammerer, Gregg, Jayaraman, Dinesh, Calandra, Roberto

“… Despite decades of research, general purpose in-hand manipulation remains one of the unsolved challenges of robotics …”
Volltext

What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction von Scholler, Christoph, Aravantinos, Vincent, Lay, Florian, Knoll, Alois

“… Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on …”
Volltext