We consider the problem of system identification of helicopter dynamics. Helicopters are complex systems, coupling rigid body dynamics with aerodynamics, engine dynamics, vibration, and other phenomena. Resultantly, they pose a challenging system identification problem, especially when considering non-stationary flight regimes. We pose the dynamics modeling problem as direct highdimensional regression, and take inspiration from recent results in Deep Learning to represent the helicopter dynamics with a Rectified Linear Unit (ReLU) Network Model, a hierarchical neural network model. We provide a simple method for initializing the parameters of the model, and optimization details for training. We describe three baseline models and show that they are significantly outperformed by the ReLU Network Model in experiments on real data, indicating the power of the model to capture useful structure in system dynamics across a rich array of aerobatic maneuvers. Specifically, the ReLU Network Model improves 58% overall in RMS acceleration prediction over state-of-the-art methods. Predicting acceleration along the helicopter’s up-down axis is empirically found to be the most difficult, and the ReLU Network Model improves by 60% over the prior state-of-the-art. We discuss explanations of these performance gains, and also investigate the impact of hyperparameters in the novel model.
Kategori: Makaleler
Makale: Learning Visual Feature Spaces for Robotic Manipulation with Deep Spatial Autoencoders
Reinforcement learning provides a powerful and flexible framework for automated acquisition of robotic motion skills. However, applying reinforcement learning requires a sufficiently detailed representation of the state, including the configuration of task-relevant objects. We present an approach that automates state-space construction by learning a state representation directly from camera images. Our method uses a deep spatial autoencoder to acquire a set of feature points that describe the environment for the current task, such as the positions of objects, and then learns a motion skill with these feature points using an efficient reinforcement learning method based on local linear models. The resulting controller reacts continuously to the learned feature points, allowing the robot to dynamically manipulate objects in the world with closed-loop control. We demonstrate our method with a PR2 robot on tasks that include pushing a free-standing toy block, picking up a bag of rice using a spatula, and hanging a loop of rope on a hook at various positions. In each task, our method automatically learns to track task-relevant objects and manipulate their configuration with the robot’s arm.
Makale: Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search
Model predictive control (MPC) is an effective method for controlling robotic systems, particularly autonomous aerial vehicles such as quadcopters. However, application of MPC can be computationally demanding, and typically requires estimating the state of the system, which can be challenging in complex, unstructured environments. Reinforcement learning can in principle forego the need for explicit state estimation and acquire a policy that directly maps sensor readings to actions, but is difficult to apply to underactuated systems that are liable to fail catastrophically during training, before an effective policy has been found. We propose to combine MPC with reinforcement learning in the framework of guided policy search, where MPC is used to generate data at training time, under full state observations provided by an instrumented training environment. This data is used to train a deep neural network policy, which is allowed to access only the raw observations from the vehicle’s onboard sensors. After training, the neural network policy can successfully control the robot without knowledge of the full state, and at a fraction of the computational cost of MPC. We evaluate our method by learning obstacle avoidance policies for a simulated quadrotor, using simulated onboard sensors and no explicit state estimation at test time.
Makale: Challenges in Representation Learning: A Report on Three Machine Learning Contests
The ICML 2013 Workshop on Challenges in Representation Learning 3 focused on three challenges: the black box learning challenge, the facial expression recognition challenge, and the multimodal learning challenge. We describe the datasets created for these challenges and summarize the results of the competitions. We provide suggestions for organizers of future challenges and some comments on what kind of knowledge can be gained from machine learning competitions.
Makale: Can Deep Learning Help You Find The Perfect Match?
Is he/she my type or not? The answer to this question depends on the personal preferences of the one asking it. The individual process of obtaining a full answer may generally be difficult and time consuming, but often an approximate answer can be obtained simply by looking at a photo of the potential match. Such approximate answers based on visual cues can be produced in a fraction of a second, a phenomenon that has led to a series of recently successful dating apps in which users rate others positively or negatively using primarily a single photo. In this paper we explore using convolutional networks to create a model of an individual’s personal preferences based on rated photos. This introduced task is difficult due to the large number of variations in profile pictures and the noise in attractiveness labels. Toward this task we collect a dataset comprised of 9364 pictures and binary labels for each. We compare performance of convolutional models trained in three ways: first directly on the collected dataset, second with features transferred from a network trained to predict gender, and third with features transferred from a network trained on ImageNet. Our findings show that ImageNet features transfer best, producing a model that attains 68.1% accuracy on the test set and is moderately successful at predicting matches.