We present a challenging dataset, the TartanAir, for robot navigation task and more. The data is collected in photo-realistic simulation environments in the presence of various light conditions, weather and moving objects. By collecting data in simulation, we are able to obtain multimodal sensor data and precise ground truth labels, including the stereo RGB image, depth image, segmentation, optical flow, camera poses, and LiDAR point cloud. We set up a large number of environments with various styles and scenes, covering challenging viewpoints and diverse motion patterns, which are difficult to achieve by using physical data collection platforms. In order to enable data collection in such large scale, we develop an automatic pipeline, including mapping, trajectory sampling, data processing, and data verification. We evaluate the impact of various factors on visual SLAM algorithms using our data. Results of state-of-the-art algorithms reveal that the visual SLAM problem is far from solved, methods that show good performance on established datasets such as KITTI don't perform well in more difficult scenarios. Although we use the simulation, our goal is to push the limits of Visual SLAM algorithms in the real world by providing a challenging benchmark for testing new methods, as well as large diverse training data for learning-based methods. Our dataset is available at http://theairlab.org/tartanair-dataset.

No abstract

No abstract

No abstract

Based on the experimental data presented in Part I, a nonlinear viscoelastic constitutive model, in differential form, is presented here. A distinctive feature of this model is the inclusion of a criterion to delineate loading and unloading in multiaxial stress states, and different moduli for loading and unloading behaviors. In addition, the model contains only five material constants and one modulus function, which can be calibrated in accordance with a well-defined procedure. A comparison with the experimental data shows that the current differential model is capable of predicting the nonlinear viscoelastic behavior of the epoxy polymer qualitatively and quantitatively, including both the loading and unloading behavior. The predictions of an integral form of constitutive model are also included for comparative purposes.

Automatic machine learning (AutoML) aims at automatically choosing the best configuration for machine learning tasks. However, a configuration evaluation can be very time consuming particularly on learning tasks with large datasets. This limitation usually restrains derivative-free optimization from releasing its full power for a fine configuration search using many evaluations. To alleviate this limitation, in this paper, we propose a derivative-free optimization framework for AutoML using multi-fidelity evaluations. It uses many lowfidelity evaluations on small data subsets and very few highfidelity evaluations on the full dataset. However, the lowfidelity evaluations can be badly biased, and need to be corrected with only a very low cost. We thus propose the Transfer Series Expansion (TSE) that learns the low-fidelity correction predictor efficiently by linearly combining a set of base predictors. The base predictors can be obtained cheaply from down-scaled and experienced tasks. Experimental results on real-world AutoML problems verify that the proposed framework can accelerate derivative-free configuration search significantly by making use of the multi-fidelity evaluations.

No abstract

Classification-based optimization is a recently developed framework for derivative-free optimization, which has shown to be effective for non-convex optimization problems with many local optima. This framework requires to sample a batch of solutions for every update of the search model. However, in reinforcement learning, direct policy search often offers only sequential policy evaluation. Thus, classificationbased optimization is not efficient for direct policy search where solutions have to be sampled sequentially. In this paper, we adapt the classification-based optimization for sequential sampled solutions by forming the batch of reused historical solutions. Experiments on helicopter hovering control task and reinforcement learning benchmark tasks in OpenAI Gym show that the new algorithm is superior to state-of-the-art derivative-free optimization approaches.