Driving in a dynamic, multi-agent, and complex urban environment is a difficult task requiring a complex decision-making policy. The learning of such a policy requires a state representation that can encode the entire environment. Mid-level representations that encode a vehicle's environment as images have become a popular choice. Still, they are quite high-dimensional, limiting their use in data-hungry approaches such as reinforcement learning. In this article, we propose to learn a low-dimensional and rich latent representation of the environment by leveraging the knowledge of relevant semantic factors. To do this, we train an encoder-decoder deep neural network to predict multiple application-relevant factors such as the trajectories of other agents and the ego car. Furthermore, we propose a hazard signal based on other vehicles' future trajectories and the planned route which is used in conjunction with the learned latent representation as input to a down-stream policy. We demonstrate that using the multi-head encoder-decoder neural network results in a more informative representation than a standard single-head model. In particular, the proposed representation learning and the hazard signal help reinforcement learning to learn faster, with increased performance and less data than baseline methods.
相關內容
Two current methods used to train autonomous cars are reinforcement learning and imitation learning. This research develops a new learning methodology and systematic approach in both a simulated and a smaller real world environment by integrating supervised imitation learning into reinforcement learning to make the RL training data collection process more effective and efficient. By combining the two methods, the proposed research successfully leverages the advantages of both RL and IL methods. First, a real mini-scale robot car was assembled and trained on a 6 feet by 9 feet real world track using imitation learning. During the process, a handle controller was used to control the mini-scale robot car to drive on the track by imitating a human expert driver and manually recorded the actions using Microsoft AirSim's API. 331 accurate human-like reward training samples were able to be generated and collected. Then, an agent was trained in the Microsoft AirSim simulator using reinforcement learning for 6 hours with the initial 331 reward data inputted from imitation learning training. After a 6-hour training period, the mini-scale robot car was able to successfully drive full laps around the 6 feet by 9 feet track autonomously while the mini-scale robot car was unable to complete one full lap round the track even after 30 hour training pure RL training. With 80% less training time, the new methodology produced significantly more average rewards per hour. Thus, the new methodology was able to save a significant amount of training time and can be used to accelerate the adoption of RL in autonomous driving, which would help produce more efficient and better results in the long run when applied to real life scenarios. Key Words: Reinforcement Learning (RL), Imitation Learning (IL), Autonomous Driving, Human Driving Data, CNN
We propose a novel framework to classify large-scale time series data with long duration. Long time seriesclassification (L-TSC) is a challenging problem because the dataoften contains a large amount of irrelevant information to theclassification target. The irrelevant period degrades the classifica-tion performance while the relevance is unknown to the system.This paper proposes an uncertainty-aware multiple instancelearning (MIL) framework to identify the most relevant periodautomatically. The predictive uncertainty enables designing anattention mechanism that forces the MIL model to learn from thepossibly discriminant period. Moreover, the predicted uncertaintyyields a principled estimator to identify whether a prediction istrustworthy or not. We further incorporate another modality toaccommodate unreliable predictions by training a separate modelbased on its availability and conduct uncertainty aware fusion toproduce the final prediction. Systematic evaluation is conductedon the Automatic Identification System (AIS) data, which is col-lected to identify and track real-world vessels. Empirical resultsdemonstrate that the proposed method can effectively detect thetypes of vessels based on the trajectory and the uncertainty-awarefusion with other available data modality (Synthetic-ApertureRadar or SAR imagery is used in our experiments) can furtherimprove the detection accuracy.
Robust Policy Search is the problem of learning policies that do not degrade in performance when subject to unseen environment model parameters. It is particularly relevant for transferring policies learned in a simulation environment to the real world. Several existing approaches involve sampling large batches of trajectories which reflect the differences in various possible environments, and then selecting some subset of these to learn robust policies, such as the ones that result in the worst performance. We propose an active learning based framework, EffAcTS, to selectively choose model parameters for this purpose so as to collect only as much data as necessary to select such a subset. We apply this framework using Linear Bandits, and experimentally validate the gains in sample efficiency and the performance of our approach on standard continuous control tasks. We also present a Multi-Task Learning perspective to the problem of Robust Policy Search, and draw connections from our proposed framework to existing work on Multi-Task Learning.
Efficient reasoning about the semantic, spatial, and temporal structure of a scene is a crucial prerequisite for autonomous driving. We present NEural ATtention fields (NEAT), a novel representation that enables such reasoning for end-to-end imitation learning models. NEAT is a continuous function which maps locations in Bird's Eye View (BEV) scene coordinates to waypoints and semantics, using intermediate attention maps to iteratively compress high-dimensional 2D image features into a compact representation. This allows our model to selectively attend to relevant regions in the input while ignoring information irrelevant to the driving task, effectively associating the images with the BEV representation. In a new evaluation setting involving adverse environmental conditions and challenging scenarios, NEAT outperforms several strong baselines and achieves driving scores on par with the privileged CARLA expert used to generate its training data. Furthermore, visualizing the attention maps for models with NEAT intermediate representations provides improved interpretability.
Training machine learning models in a meaningful order, from the easy samples to the hard ones, using curriculum learning can provide performance improvements over the standard training approach based on random data shuffling, without any additional computational costs. Curriculum learning strategies have been successfully employed in all areas of machine learning, in a wide range of tasks. However, the necessity of finding a way to rank the samples from easy to hard, as well as the right pacing function for introducing more difficult data can limit the usage of the curriculum approaches. In this survey, we show how these limits have been tackled in the literature, and we present different curriculum learning instantiations for various tasks in machine learning. We construct a multi-perspective taxonomy of curriculum learning approaches by hand, considering various classification criteria. We further build a hierarchical tree of curriculum learning methods using an agglomerative clustering algorithm, linking the discovered clusters with our taxonomy. At the end, we provide some interesting directions for future work.
Since DARPA Grand Challenges (rural) in 2004/05 and Urban Challenges in 2007, autonomous driving has been the most active field of AI applications. Almost at the same time, deep learning has made breakthrough by several pioneers, three of them (also called fathers of deep learning), Hinton, Bengio and LeCun, won ACM Turin Award in 2019. This is a survey of autonomous driving technologies with deep learning methods. We investigate the major fields of self-driving systems, such as perception, mapping and localization, prediction, planning and control, simulation, V2X and safety etc. Due to the limited space, we focus the analysis on several key areas, i.e. 2D and 3D object detection in perception, depth estimation from cameras, multiple sensor fusion on the data, feature and task level respectively, behavior modelling and prediction of vehicle driving and pedestrian trajectories.
Although deep reinforcement learning (deep RL) methods have lots of strengths that are favorable if applied to autonomous driving, real deep RL applications in autonomous driving have been slowed down by the modeling gap between the source (training) domain and the target (deployment) domain. Unlike current policy transfer approaches, which generally limit to the usage of uninterpretable neural network representations as the transferred features, we propose to transfer concrete kinematic quantities in autonomous driving. The proposed robust-control-based (RC) generic transfer architecture, which we call RL-RC, incorporates a transferable hierarchical RL trajectory planner and a robust tracking controller based on disturbance observer (DOB). The deep RL policies trained with known nominal dynamics model are transfered directly to the target domain, DOB-based robust tracking control is applied to tackle the modeling gap including the vehicle dynamics errors and the external disturbances such as side forces. We provide simulations validating the capability of the proposed method to achieve zero-shot transfer across multiple driving scenarios such as lane keeping, lane changing and obstacle avoidance.
Deep learning (DL) is a high dimensional data reduction technique for constructing high-dimensional predictors in input-output models. DL is a form of machine learning that uses hierarchical layers of latent features. In this article, we review the state-of-the-art of deep learning from a modeling and algorithmic perspective. We provide a list of successful areas of applications in Artificial Intelligence (AI), Image Processing, Robotics and Automation. Deep learning is predictive in its nature rather then inferential and can be viewed as a black-box methodology for high-dimensional function estimation.
Deep hierarchical reinforcement learning has gained a lot of attention in recent years due to its ability to produce state-of-the-art results in challenging environments where non-hierarchical frameworks fail to learn useful policies. However, as problem domains become more complex, deep hierarchical reinforcement learning can become inefficient, leading to longer convergence times and poor performance. We introduce the Deep Nested Agent framework, which is a variant of deep hierarchical reinforcement learning where information from the main agent is propagated to the low level $nested$ agent by incorporating this information into the nested agent's state. We demonstrate the effectiveness and performance of the Deep Nested Agent framework by applying it to three scenarios in Minecraft with comparisons to a deep non-hierarchical single agent framework, as well as, a deep hierarchical framework.
Multi-Task Learning (MTL) is a learning paradigm in machine learning and its aim is to leverage useful information contained in multiple related tasks to help improve the generalization performance of all the tasks. In this paper, we give a survey for MTL. First, we classify different MTL algorithms into several categories: feature learning approach, low-rank approach, task clustering approach, task relation learning approach, dirty approach, multi-level approach and deep learning approach. In order to compare different approaches, we discuss the characteristics of each approach. In order to improve the performance of learning tasks further, MTL can be combined with other learning paradigms including semi-supervised learning, active learning, reinforcement learning, multi-view learning and graphical models. When the number of tasks is large or the data dimensionality is high, batch MTL models are difficult to handle this situation and online, parallel and distributed MTL models as well as feature hashing are reviewed to reveal the computational and storage advantages. Many real-world applications use MTL to boost their performance and we introduce some representative works. Finally, we present theoretical analyses and discuss several future directions for MTL.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191