About this Research Topic
Motion planning, also known as the navigation problem, is a term used in robotics to find a sequence of valid configurations that moves the robot from the source to a destination. There are several areas of robotic applications that can benefit from better solutions to the navigation problem such as autonomy, automation, optimization, and robotic surgery. Areas of focus to optimize these applications can include: artificial intelligence, architectural design, robotic design, biological integration, and design. In this Research Topic we want to focus on the artificial intelligence aspect that creates solutions to the navigation problem.
One of the fundamental aspects of artificial intelligence is the ability to process temporal information. Because we live in a changing environment, a robot must be able to encode patterns over time to recognize and reproduce them. The sets of points that specifies the translational and rotational paths of the robot as a function of time is referred to as the trajectory. A robot trajectory may be specified as a sequence of discrete points of a temporal sequence. For this Research Topic, we hope to see focused manuscripts that use artificial intelligence for robots to learn how to develop a trajectory specifically using fast neural networks.
Fast neural networks are algorithms which accelerate trajectory learning in robots. Some examples of fast neural networks, and their variants, are fuzzy, deep, kalman filter, recursive least squares, backpropagation, convolutional, genetic, adam, stochastic, and clustering. The goal of this Research Topic is to welcome research on different types of robots that use fast neural networks to learn and retrieve trajectories in order to perform a positioning task of a robot and contribute solutions to the navigation problems.
We welcome all articles of these topics. Potential topics include, but are not limited to the following:
1. Fast neural networks for the trajectory learning in robotic manipulators
2. Fast neural networks for the trajectory learning in mobile robots
3. Fast neural networks for the trajectory learning in quadrotors
4. Fast neural networks for the trajectory learning in other robots
5. Fast neural networks for the trajectory optimization
6. Fast neural networks for the trajectory tracking
One of the fundamental aspects of artificial intelligence is the ability to process temporal information. Because we live in a changing environment, a robot must be able to encode patterns over time to recognize and reproduce them. The sets of points that specifies the translational and rotational paths of the robot as a function of time is referred to as the trajectory. A robot trajectory may be specified as a sequence of discrete points of a temporal sequence. For this Research Topic, we hope to see focused manuscripts that use artificial intelligence for robots to learn how to develop a trajectory specifically using fast neural networks.
Fast neural networks are algorithms which accelerate trajectory learning in robots. Some examples of fast neural networks, and their variants, are fuzzy, deep, kalman filter, recursive least squares, backpropagation, convolutional, genetic, adam, stochastic, and clustering. The goal of this Research Topic is to welcome research on different types of robots that use fast neural networks to learn and retrieve trajectories in order to perform a positioning task of a robot and contribute solutions to the navigation problems.
We welcome all articles of these topics. Potential topics include, but are not limited to the following:
1. Fast neural networks for the trajectory learning in robotic manipulators
2. Fast neural networks for the trajectory learning in mobile robots
3. Fast neural networks for the trajectory learning in quadrotors
4. Fast neural networks for the trajectory learning in other robots
5. Fast neural networks for the trajectory optimization
6. Fast neural networks for the trajectory tracking
Keywords: Trajectories learning, Neural networks, Robots
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
