While imitation learning for vision based autonomous mobile robot navigation has recently received a great deal of attention in the research community, existing approaches typically require state action demonstrations that were gathered using the deployment platform. However, what if one cannot easily outfit their platform to record these demonstration signals or worse yet the demonstrator does not have access to the platform at all? Is imitation learning for vision based autonomous navigation even possible in such scenarios? In this work, we hypothesize that the answer is yes and that recent ideas from the Imitation from Observation (IfO) literature can be brought to bear such that a robot can learn to navigate using only ego centric video collected by a demonstrator, even in the presence of viewpoint mismatch. To this end, we introduce a new algorithm, Visual Observation only Imitation Learning for Autonomous navigation (VOILA), that can successfully learn navigation policies from a single video demonstration collected from a physically different agent. We evaluate VOILA in the photorealistic AirSim simulator and show that VOILA not only successfully imitates the expert, but that it also learns navigation policies that can generalize to novel environments. Further, we demonstrate the effectiveness of VOILA in a real world setting by showing that it allows a wheeled Jackal robot to successfully imitate a human walking in an environment using a video recorded using a mobile phone camera.
相關內容
In this paper, we present a complete autonomous navigation pipeline for unstructured outdoor environments. The main contribution of this work is on the path planning module, which we divided into two main categories: Global Path Planning (GPP) and Local Path Planning (LPP). For environment representation, instead of complex and heavy grid maps, the GPP layer uses road network information obtained directly from OpenStreetMaps (OSM). In the LPP layer, we use a novel Naive-Valley-Path (NVP) method to generate a local path avoiding obstacles in the road in real-time. This approach uses a naive representation of the local environment using a LiDAR sensor. Also, it uses a naive optimization that exploits the concept of "valley" areas in the cost map. We demonstrate the system's robustness experimentally in our research platform BLUE, driving autonomously across the University of Alicante Scientific Park for more than 20 km in a 12.33 ha area.
Many reinforcement learning (RL) environments consist of independent entities that interact sparsely. In such environments, RL agents have only limited influence over other entities in any particular situation. Our idea in this work is that learning can be efficiently guided by knowing when and what the agent can influence with its actions. To achieve this, we introduce a measure of \emph{situation-dependent causal influence} based on conditional mutual information and show that it can reliably detect states of influence. We then propose several ways to integrate this measure into RL algorithms to improve exploration and off-policy learning. All modified algorithms show strong increases in data efficiency on robotic manipulation tasks.
Autonomous vehicles (AVs) must interact with a diverse set of human drivers in heterogeneous geographic areas. Ideally, fleets of AVs should share trajectory data to continually re-train and improve trajectory forecasting models from collective experience using cloud-based distributed learning. At the same time, these robots should ideally avoid uploading raw driver interaction data in order to protect proprietary policies (when sharing insights with other companies) or protect driver privacy from insurance companies. Federated learning (FL) is a popular mechanism to learn models in cloud servers from diverse users without divulging private local data. However, FL is often not robust -- it learns sub-optimal models when user data comes from highly heterogeneous distributions, which is a key hallmark of human-robot interactions. In this paper, we present a novel variant of personalized FL to specialize robust robot learning models to diverse user distributions. Our algorithm outperforms standard FL benchmarks by up to 2x in real user studies that we conducted where human-operated vehicles must gracefully merge lanes with simulated AVs in the standard CARLA and CARLO AV simulators.
Autonomous unmanned aerial vehicle (UAV) inertial navigation exhibits an extreme dependency on the availability of global navigation satellite systems (GNSS) signals, without which it incurs in a slow but unavoidable position drift that may ultimately lead to the loss of the platform if the GNSS signals are not restored or the aircraft does not reach a location from which it can be recovered by remote control. This article describes an stochastic high fidelity simulation of the flight of a fixed wing low SWaP (size, weight, and power) autonomous UAV in turbulent and varying weather intended to test and validate the GNSS-Denied performance of different navigation algorithms. Its open-source \nm{\CC} implementation has been released and is publicly available. Onboard sensors include accelerometers, gyroscopes, magnetometers, a Pitot tube, an air data system, a GNSS receiver, and a digital camera, so the simulation is valid for inertial, visual, and visual inertial navigation systems. Two scenarios involving the loss of GNSS signals are considered: the first represents the challenges involved in aborting the mission and heading towards a remote recovery location while experiencing varying weather, and the second models the continuation of the mission based on a series of closely spaced bearing changes. All simulation modules have been modeled with as few simplifications as possible to increase the realism of the results. While the implementation of the aircraft performances and its control system is deterministic, that of all other modules, including the mission, sensors, weather, wind, turbulence, and initial estimations, is fully stochastic. This enables a robust evaluation of each proposed navigation system by means of Monte-Carlo simulations that rely on a high number of executions of both scenarios.
The challenges presented in an autonomous racing situation are distinct from those faced in regular autonomous driving and require faster end-to-end algorithms and consideration of a longer horizon in determining optimal current actions keeping in mind upcoming maneuvers and situations. In this paper, we propose an end-to-end method for autonomous racing that takes in as inputs video information from an onboard camera and determines final steering and throttle control actions. We use the following split to construct such a method (1) learning a low dimensional representation of the scene, (2) pre-generating the optimal trajectory for the given scene, and (3) tracking the predicted trajectory using a classical control method. In learning a low-dimensional representation of the scene, we use intermediate representations with a novel unsupervised trajectory planner to generate expert trajectories, and hence utilize them to directly predict race lines from a given front-facing input image. Thus, the proposed algorithm employs the best of two worlds - the robustness of learning-based approaches to perception and the accuracy of optimization-based approaches for trajectory generation in an end-to-end learning-based framework. We deploy and demonstrate our framework on CARLA, a photorealistic simulator for testing self-driving cars in realistic environments.
Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. To tackle this issue, we propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress about training samples. We develop the principle of curriculum design and re-arrange the benchmark Room-to-Room (R2R) dataset to make it suitable for curriculum training. Experiments show that our method is model-agnostic and can significantly improve the performance, the generalizability, and the training efficiency of current state-of-the-art navigation agents without increasing model complexity.
Breakthroughs in machine learning in the last decade have led to `digital intelligence', i.e. machine learning models capable of learning from vast amounts of labeled data to perform several digital tasks such as speech recognition, face recognition, machine translation and so on. The goal of this thesis is to make progress towards designing algorithms capable of `physical intelligence', i.e. building intelligent autonomous navigation agents capable of learning to perform complex navigation tasks in the physical world involving visual perception, natural language understanding, reasoning, planning, and sequential decision making. Despite several advances in classical navigation methods in the last few decades, current navigation agents struggle at long-term semantic navigation tasks. In the first part of the thesis, we discuss our work on short-term navigation using end-to-end reinforcement learning to tackle challenges such as obstacle avoidance, semantic perception, language grounding, and reasoning. In the second part, we present a new class of navigation methods based on modular learning and structured explicit map representations, which leverage the strengths of both classical and end-to-end learning methods, to tackle long-term navigation tasks. We show that these methods are able to effectively tackle challenges such as localization, mapping, long-term planning, exploration and learning semantic priors. These modular learning methods are capable of long-term spatial and semantic understanding and achieve state-of-the-art results on various navigation tasks.
Deep neural networks (DNNs) are found to be vulnerable against adversarial examples, which are carefully crafted inputs with a small magnitude of perturbation aiming to induce arbitrarily incorrect predictions. Recent studies show that adversarial examples can pose a threat to real-world security-critical applications: a "physical adversarial Stop Sign" can be synthesized such that the autonomous driving cars will misrecognize it as others (e.g., a speed limit sign). However, these image-space adversarial examples cannot easily alter 3D scans of widely equipped LiDAR or radar on autonomous vehicles. In this paper, we reveal the potential vulnerabilities of LiDAR-based autonomous driving detection systems, by proposing an optimization based approach LiDAR-Adv to generate adversarial objects that can evade the LiDAR-based detection system under various conditions. We first show the vulnerabilities using a blackbox evolution-based algorithm, and then explore how much a strong adversary can do, using our gradient-based approach LiDAR-Adv. We test the generated adversarial objects on the Baidu Apollo autonomous driving platform and show that such physical systems are indeed vulnerable to the proposed attacks. We also 3D-print our adversarial objects and perform physical experiments to illustrate that such vulnerability exists in the real world. Please find more visualizations and results on the anonymous website: //sites.google.com/view/lidar-adv.
Vision-language navigation (VLN) is the task of navigating an embodied agent to carry out natural language instructions inside real 3D environments. In this paper, we study how to address three critical challenges for this task: the cross-modal grounding, the ill-posed feedback, and the generalization problems. First, we propose a novel Reinforced Cross-Modal Matching (RCM) approach that enforces cross-modal grounding both locally and globally via reinforcement learning (RL). Particularly, a matching critic is used to provide an intrinsic reward to encourage global matching between instructions and trajectories, and a reasoning navigator is employed to perform cross-modal grounding in the local visual scene. Evaluation on a VLN benchmark dataset shows that our RCM model significantly outperforms existing methods by 10% on SPL and achieves the new state-of-the-art performance. To improve the generalizability of the learned policy, we further introduce a Self-Supervised Imitation Learning (SIL) method to explore unseen environments by imitating its own past, good decisions. We demonstrate that SIL can approximate a better and more efficient policy, which tremendously minimizes the success rate performance gap between seen and unseen environments (from 30.7% to 11.7%).
Neural Network Based Reinforcement Learning for Audio-Visual Gaze Control in Human-Robot Interaction
This paper introduces a novel neural network-based reinforcement learning approach for robot gaze control. Our approach enables a robot to learn and to adapt its gaze control strategy for human-robot interaction neither with the use of external sensors nor with human supervision. The robot learns to focus its attention onto groups of people from its own audio-visual experiences, independently of the number of people, of their positions and of their physical appearances. In particular, we use a recurrent neural network architecture in combination with Q-learning to find an optimal action-selection policy; we pre-train the network using a simulated environment that mimics realistic scenarios that involve speaking/silent participants, thus avoiding the need of tedious sessions of a robot interacting with people. Our experimental evaluation suggests that the proposed method is robust against parameter estimation, i.e. the parameter values yielded by the method do not have a decisive impact on the performance. The best results are obtained when both audio and visual information is jointly used. Experiments with the Nao robot indicate that our framework is a step forward towards the autonomous learning of socially acceptable gaze behavior.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191