Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments

Chen, Xi; Ghadirzadeh, Ali; Folkesson, John; Björkman, Mårten; Jensfelt, Patric

doi:10.1109/iros.2018.8593702

Cited by 39 publications

(30 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chen et al [12] deployed also PPO for deep RL as we do. The authors rely on height-map observations as state representation for a wheel-legged robot.…”

Section: Related Workmentioning

confidence: 98%

Deep Reinforcement Learning for Navigation in Cluttered Environments

Seguchi¹,

Gesing²,

Bennewitz³

et al. 2020

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

Collision-free motion is essential for mobile robots. Most approaches to collision-free and efficient navigation with wheeled robots require parameter tuning by experts to obtain good navigation behavior. In this paper, we aim at learning an optimal navigation policy by deep reinforcement learning to overcome this manual parameter tuning. Our approach uses proximal policy optimization to train the policy and achieve collision-free and goal-directed behavior. The output of the learned network are the robot's translational and angular velocities for the next time step. Our method combines path planning on a 2D grid with reinforcement learning and does not need any supervision. Our network is first trained in a simple environment and then transferred to scenarios of increasing complexity. We implemented our approach in C++ and Python for the Robot Operating System (ROS) and thoroughly tested it in several simulated as well as real-world experiments. The experiments illustrate that our trained policy can be applied to solve complex navigation tasks. Furthermore, we compare the performance of our learned controller to the popular dynamic window approach (DWA) of ROS. As the experimental results show, a robot controlled by our learned policy reaches the goal significantly faster compared to using the DWA by closely bypassing obstacles and thus saving time.

show abstract

“…Chen et al [12] deployed also PPO for deep RL as we do. The authors rely on height-map observations as state representation for a wheel-legged robot.…”

Section: Related Workmentioning

confidence: 98%

Deep Reinforcement Learning for Navigation in Cluttered Environments

Seguchi¹,

Gesing²,

Bennewitz³

et al. 2020

Computer Science &Amp; Information Technology (CS &Amp; IT)

View full text Add to dashboard Cite

show abstract

“…Kalashnikov et al used a scalable RL framework for learning vision-based dynamic grasping skills [17]. However, it is required lots of exploration to obtain a skill via an RL manner integrated with visuomotor framework, which is regarded to be data-inefficient [18,19].…”

Section: Related Workmentioning

confidence: 99%

Object Detection-Based One-Shot Imitation Learning with an RGB-D Camera

Shao

et al. 2020

Applied Sciences

View full text Add to dashboard Cite

End-to-end robot learning has achieved a great success for robots to obtain various manipulation skills. It learns a function which maps visual information to robotic action directly. Because of the diversity of target objects, most end-to-end robot learning approaches have focused on a single object-specific task with a limited capability of generalization. In this work, an object detection-based one-shot learning method is proposed, which separates the semantic understanding from robot control. It enables a robot to acquire similar manipulation skills efficiently and to have the ability to cope with new objects with a single demonstration. This approach mainly has two modules: the object detection network and the motion policy network. With RGB images, the object detection network tries to output the task-related semantic keypoint of the target object, which is the center of the container in this application, and the motion policy network generates the motion action based on the depth map and the detected keypoint. To evaluate this proposed pipeline, a series of experiments are conducted on typical placing tasks in different simulation scenarios and, additionally, the learned policy is transferred from simulation to the real world without any fine-tuning.

show abstract

“…However, our goal is to find a policy which is independent on the strip properties. One possibility of finding such a policy is to use domain randomization [18], [19]. Domain randomization for our task may be achieved by modifying the optimization (2) into:…”

Section: B Domain Randomizationmentioning

confidence: 99%

Feedback-based Fabric Strip Folding

Petrík

Kyrki

2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Accurate manipulation of a deformable body such as a piece of fabric is difficult because of its many degrees of freedom and unobservable properties affecting its dynamics. To alleviate these challenges, we propose the application of feedback-based control to robotic fabric strip folding. The feedback is computed from the low dimensional state extracted from a camera image. We trained the controller using reinforcement learning in simulation which was calibrated to cover the real fabric strip behaviors. The proposed feedback-based folding was experimentally compared to two state-of-the-art folding methods and our method outperformed both of them in terms of accuracy.

show abstract

Deep Reinforcement Learning to Acquire Navigation Skills for Wheel-Legged Robots in Complex Environments

Cited by 39 publications

References 38 publications

Deep Reinforcement Learning for Navigation in Cluttered Environments

Deep Reinforcement Learning for Navigation in Cluttered Environments

Object Detection-Based One-Shot Imitation Learning with an RGB-D Camera

Feedback-based Fabric Strip Folding

Contact Info

Product

Resources

About