scholarly journals Adjustable and Adaptive Control for an Unstable Mobile Robot Using Imitation Learning with Trajectory Optimization

Robotics ◽  
2020 ◽  
Vol 9 (2) ◽  
pp. 29
Author(s):  
Christian Dengler ◽  
Boris Lohmann
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Trajectory Optimization ◽  
Inverted Pendulum ◽  
Gradient Methods ◽  
Real System ◽  
Fine Tuning ◽  
Imitation Learning ◽  
Parametric Function ◽  
The Real

In this contribution, we develop a feedback controller in the form of a parametric function for a mobile inverted pendulum. The control both stabilizes the system and drives it to target positions with target orientations. A design of the controller based only on a cost function is difficult for this task, which is why we choose to train the controller using imitation learning on optimized trajectories. In contrast to popular approaches like policy gradient methods, this approach allows us to shape the behavior of the system by including equality constraints. When transferring the parametric controller from simulation to the real mobile inverted pendulum, the control performance is degraded due to the reality gap. A robust control design can reduce the degradation. However, for the framework of imitation learning on optimized trajectories, methods that explicitly consider robustness do not yet exist to the knowledge of the authors. We tackle this research gap by presenting a method to design a robust controller in the form of a recurrent neural network, to improve the transferability of the trained controller to the real system. As a last step, we make the behavior of the parametric controller adjustable to allow for the fine tuning of the behavior of the real system. We design the controller for our system and show in the application that the recurrent neural network has increased performance compared to a static neural network without robustness considerations.

Earth–Moon low energy trajectory optimization in the real system

2013 ◽  
Vol 51 (5) ◽  
pp. 917-929 ◽  
Author(s):  
Hanlun Lei ◽  
Bo Xu ◽  
Yisui Sun
Keyword(s):  
Trajectory Optimization ◽  
Low Energy ◽  
Real System ◽  
The Real

scholarly journals Spiking recurrent neural networks represent task-relevant neural sequences in rule-dependent computation

2021 ◽  
Author(s):  
Xiaohe Xue ◽  
Michael M. Halassa ◽  
Zhe S. Chen
Keyword(s):  
Neural Network ◽  
Decision Making ◽  
Working Memory ◽  
Recurrent Neural Network ◽  
Cortical Neurons ◽  
Gradient Methods ◽  
Cognitive Tasks ◽  
Brain Functions ◽  
Neural Representations ◽  
Biological Constraints

AbstractPrefrontal cortical neurons play in important roles in performing rule-dependent tasks and working memory-based decision making. Motivated by experimental data, we develop an excitatory-inhibitory spiking recurrent neural network (SRNN) to perform a rule-dependent two-alternative forced choice (2AFC) task. We imposed several important biological constraints onto the SRNN, and adapted the spike frequency adaptation (SFA) and SuperSpike gradient methods to update the network parameters. These proposed strategies enabled us to train the SRNN efficiently and overcome the vanishing gradient problem during error back propagation through time. The trained SRNN produced rule-specific tuning in single-unit representations, showing rule-dependent population dynamics that strongly resemble experimentally observed data in rodent and monkey. Under varying test conditions, we further manipulated the parameters or configuration in computer simulation setups and investigated the impacts of rule-coding error, delay duration, weight connectivity and sparsity, and excitation/inhibition (E/I) balance on both task performance and neural representations. Overall, our modeling study provides a computational framework to understand neuronal representations at a fine timescale during working memory and cognitive control.Author SummaryWorking memory and decision making are fundamental cognitive functions of the brain, but the circuit mechanisms of these brain functions remain incompletely understood. Neuroscientists have trained animals (rodents or monkeys) to perform various cognitive tasks while simultaneously recording the neural activity from specific neural circuits. To complement the experimental investigations, computational modeling may provide an alternative way to examine the neural representations of neuronal assemblies during task behaviors. Here we develop and train a spiking recurrent neural network (SRNN) consisting of balanced excitatory and inhibitory neurons to perform the rule-dependent working memory tasks Our computer simulations produce qualitatively similar results as the experimental findings. Moreover, the imposed biological constraints on the trained network provide additional channel to investigate cell type-specific population responses, cortical connectivity and robustness. Our work provides a computational platform to investigate neural representations and dynamics of cortical circuits a fine timescale during complex cognitive tasks.

Recurrent neural network pruning using dynamical systems and iterative fine-tuning

2021 ◽  
Author(s):  
Christos Chatzikonstantinou ◽  
Dimitrios Konstantinidis ◽  
Kosmas Dimitropoulos ◽  
Petros Daras
Keyword(s):  
Neural Network ◽  
Dynamical Systems ◽  
Recurrent Neural Network ◽  
Fine Tuning ◽  
Network Pruning

Neural-network-based real-time trajectory replanning for Mars entry guidance

2016 ◽  
Vol 231 (14) ◽  
pp. 2634-2645
Author(s):  
X Zheng ◽  
H Huang ◽  
W Li
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Trajectory Optimization ◽  
Reference Trajectory ◽  
The Real ◽  
The Neural Network ◽  
Entry Guidance ◽  
Computational Speed ◽  
Uncertain Factor ◽  
Predictor Corrector

The real-time trajectory replanning method which is used for the guidance of Mars entry is investigated in this paper. Comparing with the traditional Mars entry guidance methods, such as the reference-trajectory tracking guidance and predictor–corrector guidance, the real-time trajectory replanning method can increase the reliability of the mission remarkably. When faults occur during the Mars entry phase, a replacement trajectory will be planned quickly. Due to the limited onboard computing capacity, replanning the trajectory onboard is a challenging task. Corresponding to this problem, the neural network is trained to approximate the dynamics of the atmospheric entry. The uncertain factor of the atmospheric density is also included in the neural network. Then, by using the characters of the neural network, the analytical expressions of the Jacobian which are needed in trajectory optimization are derived. Finally, an estimation-replanning guidance procedure is introduced. The numerical simulation shows that the proposed guidance strategy can decrease the error of final states effectively, and the neural network approximation improves the computational speed of the nonlinear programming solver remarkably, which makes the method more suitable for use onboard.

Research on behavior recognition based on feature fusion of automatic coder and recurrent neural network

2020 ◽  
Vol 39 (6) ◽  
pp. 8927-8935
Author(s):  
Bing Zheng ◽  
Dawei Yun ◽  
Yan Liang
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Behavior Pattern ◽  
Rapid Development ◽  
Video Data ◽  
Support Vector ◽  
Behavior Recognition ◽  
Learning Methods ◽  
The Impact ◽  
Internet Of Things Technology

Under the impact of COVID-19, research on behavior recognition are highly needed. In this paper, we combine the algorithm of self-adaptive coder and recurrent neural network to realize the research of behavior pattern recognition. At present, most of the research of human behavior recognition is focused on the video data, which is based on the video number. At the same time, due to the complexity of video image data, it is easy to violate personal privacy. With the rapid development of Internet of things technology, it has attracted the attention of a large number of experts and scholars. Researchers have tried to use many machine learning methods, such as random forest, support vector machine and other shallow learning methods, which perform well in the laboratory environment, but there is still a long way to go from practical application. In this paper, a recursive neural network algorithm based on long and short term memory (LSTM) is proposed to realize the recognition of behavior patterns, so as to improve the accuracy of human activity behavior recognition.

Sign in / Sign up

Export Citation Format

Share Document