Learning Manipulation Trajectories Using Recurrent Neural Networks
Explore this paper's citation graph
Summary
Experiments show that the robot can learn the manipulation planning as well the ability to recover from failure, and an end-to-end learning mechanism for the type of complex robot arm trajectories used in manipulation tasks for assistive robots is proposed.
- Type
- preprint
- Published
- 2016-03-12
- Cited by
- 14
- References
- 46
- Access
- Open access
- OpenAlex
- https://openalex.org/W2297709227
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:15265943
Keywords
Task (project management), Computer science, Trajectory, Robot, Recurrent neural network
References
- IEEE International Conference on Robotics and Automation (ICRA) におけるフルードパワー技術の研究動向
- Mixture density networks
- Robot Programming by Demonstration with Crowdsourced Action Fixes
- Generating Sequences With Recurrent Neural Networks
- Show and tell: A neural image caption generator
- Robobarista: Object Part Based Transfer of Manipulation Trajectories from Crowd-Sourcing in 3D Pointclouds
- A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning
- Long-term recurrent convolutional networks for visual recognition and description
- Visualizing and Understanding Recurrent Networks
- A System for Robotic Heart Surgery that Learns to Tie Knots Using Recurrent Neural Networks
- A survey of robot learning from demonstration
- Cloud-based robot grasping with the google object recognition engine
- Learning the dynamics of doors for robotic manipulation
- Human and robot perception in large-scale learning from demonstration
- Long Short-Term Memory
- Humanoid robots learning to walk faster: from the real world to simulation and back
- Blocks and Fuel: Frameworks for deep learning
- A Novel Connectionist System for Unconstrained Handwriting Recognition
- On Learning, Representing, and Generalizing a Task in a Humanoid Robot
- Handling of multiple constraints and motion alternatives in a robot programming by demonstration framework
Cited by
- Real-time placement of a wheelchair-mounted robotic arm
- Imitation Learning
- Fast and Stable Learning of Dynamical Systems Based on Extreme Learning Machine
- Avoidance of Manual Labeling in Robotic Autonomous Navigation Through Multi-Sensory Semi-Supervised Learning
- Robot Learning from Human Demonstration: Interpretation, Adaptation, and Interaction
- Deep learning based approaches for imitation learning
- Auto-conditioned Recurrent Mixture Density Networks for Complex Trajectory Generation
- Trajectory-based Learning for Ball-in-Maze Games
- Auto-conditioned Recurrent Mixture Density Networks for Learning Generalizable Robot Skills
- Accurate Pouring using Model Predictive Control Enabled by Recurrent Neural Network
- Human-in-the-Loop Methods for Data-Driven and Reinforcement Learning Systems
- Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning
- A Survey of Demonstration Learning
- A survey of demonstration learning
- Play it by Ear: Learning Skills amidst Occlusion through Audio-Visual Imitation Learning
- Combining Learning From Human Feedback and Knowledge Engineering to Solve Hierarchical Tasks in Minecraft
- Imitation Learning:A Survey of Learning Methods
Related papers
- Learning Macros for Multi-Robot Manipulation Tasks
- Robot Task Learning from Human Demonstration
- The Benefits of Immersive Demonstrations for Teaching Robots
- Feeling the force: Integrating force and pose for fluent discovery through imitation learning to open medicine bottles
- Robustness via Retrying: Closed-Loop Robotic Manipulation with Self-Supervised Learning