Estimating 3D orientation and translation of objects is essential for infrastructure-less autonomous navigation and driving. In case of monocular vision, successful methods have been mainly based on two ingredients: (i) a network generating 2D region proposals, (ii) a R-CNN structure predicting 3D object pose by utilizing the acquired regions of interest. We argue that the 2D detection network is redundant and introduces non-negligible noise for 3D detection. Hence, we propose a novel 3D object detection method, named SMOKE, in this paper that predicts a 3D bounding box for each detected object by combining a single keypoint estimate with regressed 3D variables. As a second contribution, we propose a multi-step disentangling approach for constructing the 3D bounding box, which significantly improves both training convergence and detection accuracy. In contrast to previous 3D detection techniques, our method does not require complicated pre/post-processing, extra data, and a refinement stage. Despite of its structural simplicity, our proposed SMOKE network outperforms all existing monocular 3D detection methods on the KITTI dataset, giving the best state-of-the-art result on both 3D object detection and Bird's eye view evaluation. The code will be made publicly available.
Recent deep neural networks based techniques, especially those equipped with the ability of self-adaptation in the system level such as deep reinforcement learning (DRL), are shown to possess many advantages of optimizing robot learning systems (e.g., autonomous navigation and continuous robot arm control.) However, the learning-based systems and the associated models may be threatened by the risks of intentionally adaptive (e.g., noisy sensor confusion) and adversarial perturbations from real-world scenarios. In this paper, we introduce timing-based adversarial strategies against a DRL-based navigation system by jamming in physical noise patterns on the selected time frames. To study the vulnerability of learning-based navigation systems, we propose two adversarial agent models: one refers to online learning; another one is based on evolutionary learning. Besides, three open-source robot learning and navigation control environments are employed to study the vulnerability under adversarial timing attacks. Our experimental results show that the adversarial timing attacks can lead to a significant performance drop, and also suggest the necessity of enhancing the robustness of robot learning systems.
Robots navigating autonomously need to perceive and track the motion of objects and other agents in its surroundings. This information enables planning and executing robust and safe trajectories. To facilitate these processes, the motion should be perceived in 3D Cartesian space. However, most recent multi-object tracking (MOT) research has focused on tracking people and moving objects in 2D RGB video sequences. In this work we present JRMOT, a novel 3D MOT system that integrates information from RGB images and 3D point clouds to achieve real-time, state-of-the-art tracking performance. Our system is built with recent neural networks for re-identification, 2D and 3D detection and track description, combined into a joint probabilistic data-association framework within a multi-modal recursive Kalman architecture. As part of our work, we release the JRDB dataset, a novel large scale 2D+3D dataset and benchmark, annotated with over 2 million boxes and 3500 time consistent 2D+3D trajectories across 54 indoor and outdoor scenes. JRDB contains over 60 minutes of data including 360 degree cylindrical RGB video and 3D pointclouds in social settings that we use to develop, train and evaluate JRMOT. The presented 3D MOT system demonstrates state-of-the-art performance against competing methods on the popular 2D tracking KITTI benchmark and serves as first 3D tracking solution for our benchmark. Real-robot tests on our social robot JackRabbot indicate that the system is capable of tracking multiple pedestrians fast and reliably. We provide the ROS code of our tracker at https://sites.google.com/view/jrmot.
Capsule Networks (CapsNets) have been proposed as an alternative to Convolutional Neural Networks (CNNs). This paper showcases how CapsNets are more capable than CNNs for autonomous agent exploration of realistic scenarios. In real world navigation, rewards external to agents may be rare. In turn, reinforcement learning algorithms can struggle to form meaningful policy functions. This paper's approach Capsules Exploration Module (Caps-EM) pairs a CapsNets architecture with an Advantage Actor Critic algorithm. Other approaches for navigating sparse environments require intrinsic reward generators, such as the Intrinsic Curiosity Module (ICM) and Augmented Curiosity Modules (ACM). Caps-EM uses a more compact architecture without need for intrinsic rewards. Tested using ViZDoom, the Caps-EM uses 44% and 83% fewer trainable network parameters than the ICM and Depth-Augmented Curiosity Module (D-ACM), respectively, for 1141% and 437% average time improvement over the ICM and D-ACM, respectively, for converging to a policy function across "My Way Home" scenarios.
This paper focuses on real-time occupancy mapping and collision checking onboard an autonomous robot navigating in an unknown environment. We propose a new map representation, in which occupied and free space are separated by the decision boundary of a kernel perceptron classifier. We develop an online training algorithm that maintains a very sparse set of support vectors to represent obstacle boundaries in configuration space. We also derive conditions that allow complete (without sampling) collision-checking for piecewise-linear and piecewise-polynomial robot trajectories. We demonstrate the effectiveness of our mapping and collision checking algorithms for autonomous navigation of an Ackermann-drive robot in unknown environments.
An autonomous navigation system relies on a number of sensors including radar, LIDAR and a visible light camera for its operation. We focus our attention on the visible light camera in this work. Object detection is the key first step to processing the video input from the camera. Specifically, we address the problem of assessing the performance of object detection algorithms in hazardous driving conditions that an autonomous navigation system is expected to encounter in a realistic scenario. To this end, we propose a novel metric for quantifying the degradation in performance of an object detection algorithm under different weather conditions. Additionally' we introduce a real-time method to detect extreme variations in performance of the algorithm that can be used to issue an alert. We evaluate the performance of our metric and alerting system and demonstrate its utility using the YOLOv2 object detection algorithm trained on the KITTI and virtual KITTI dataset.
Small, carefully crafted perturbations called adversarial perturbations can easily fool neural networks. However, these perturbations are largely additive and not naturally found. We turn our attention to the field of Autonomous navigation wherein adverse weather conditions such as fog have a drastic effect on the predictions of these systems. These weather conditions are capable of acting like natural adversaries that can help in testing models. To this end, we introduce a general notion of adversarial perturbations, which can be created using generative models and provide a methodology inspired by Cycle-Consistent Generative Adversarial Networks to generate adversarial weather conditions for a given image. Our formulation and results show that these images provide a suitable testbed for steering models used in Autonomous navigation models. Our work also presents a more natural and general definition of Adversarial perturbations based on Perceptual Similarity.
Acquiring information about the road lane structure is a crucial step for autonomous navigation. To this end, several approaches tackle this task from different perspectives such as lane marking detection or semantic lane segmentation. However, to the best of our knowledge, there is yet no purely vision based end-to-end solution to answer the precise question: How to estimate the relative number or "ID" of the current driven lane within a multi-lane road or a highway? In this work, we propose a real-time, vision-only (i.e. monocular camera) solution to the problem based on a dual left-right convention. We interpret this task as a classification problem by limiting the maximum number of lane candidates to eight. Our approach is designed to meet low-complexity specifications and limited runtime requirements. It harnesses the temporal dimension inherent to the input sequences to improve upon high-complexity state-of-the-art models. We achieve more than 95% accuracy on a challenging test set with extreme conditions and different routes.
While machine learning is traditionally a resource intensive task, embedded systems, autonomous navigation, and the vision of the Internet of Things fuel the interest in resource-efficient approaches. These approaches aim for a carefully chosen trade-off between performance and resource consumption in terms of computation and energy. The development of such approaches is among the major challenges in current machine learning research and key to ensure a smooth transition of machine learning technology from a scientific environment with virtually unlimited computing resources into everyday's applications. In this article, we provide an overview of the current state of the art of machine learning techniques facilitating these real-world requirements. In particular, we focus on resource-efficient inference based on deep neural networks (DNNs), the predominant machine learning models of the past decade. We give a comprehensive overview of the vast literature that can be mainly split into three non-mutually exclusive categories: (i) quantized neural networks, (ii) network pruning, and (iii) structural efficiency. These techniques can be applied during training or as post-processing, and they are widely used to reduce the computational demands in terms of memory footprint, inference speed, and energy efficiency. We also briefly discuss different concepts of embedded hardware for DNNs and their compatibility with machine learning techniques as well as potential for energy and latency reduction. We substantiate our discussion with experiments on well-known benchmark data sets using compression techniques (quantization, pruning) for a set of resource-constrained embedded systems, such as CPUs, GPUs and FPGAs. The obtained results highlight the difficulty of finding good trade-offs between resource efficiency and prediction quality.
The ability to autonomously explore and navigate a physical space is a fundamental requirement for virtually any mobile autonomous agent, from household robotic vacuums to autonomous vehicles. Traditional SLAM-based approaches for exploration and navigation largely focus on leveraging scene geometry, but fail to model dynamic objects (such as other agents) or semantic constraints (such as wet floors or doorways). Learning-based RL agents are an attractive alternative because they can incorporate both semantic and geometric information, but are notoriously sample inefficient, difficult to generalize to novel settings, and are difficult to interpret. In this paper, we combine the best of both worlds with a modular approach that learns a spatial representation of a scene that is trained to be effective when coupled with traditional geometric planners. Specifically, we design an agent that learns to predict a spatial affordance map that elucidates what parts of a scene are navigable through active self-supervised experience gathering. In contrast to most simulation environments that assume a static world, we evaluate our approach in the VizDoom simulator, using large-scale randomly-generated maps containing a variety of dynamic actors and hazards. We show that learned affordance maps can be used to augment traditional approaches for both exploration and navigation, providing significant improvements in performance.
Autonomous systems possess the features of inferring their own state, understanding their surroundings, and performing autonomous navigation. With the applications of learning systems, like deep learning and reinforcement learning, the visual-based self-state estimation, environment perception and navigation capabilities of autonomous systems have been efficiently addressed, and many new learning-based algorithms have surfaced with respect to autonomous visual perception and navigation. In this review, we focus on the applications of learning-based monocular approaches in ego-motion perception, environment perception and navigation in autonomous systems, which is different from previous reviews that discussed traditional methods. First, we delineate the shortcomings of existing classical visual simultaneous localization and mapping (vSLAM) solutions, which demonstrate the necessity to integrate deep learning techniques. Second, we review the visual-based environmental perception and understanding methods based on deep learning, including deep learning-based monocular depth estimation, monocular ego-motion prediction, image enhancement, object detection, semantic segmentation, and their combinations with traditional vSLAM frameworks. Then, we focus on the visual navigation based on learning systems, mainly including reinforcement learning and deep reinforcement learning. Finally, we examine several challenges and promising directions discussed and concluded in related research of learning systems in the era of computer science and robotics.
Obstacle detection by semantic segmentation shows a great promise for autonomous navigation in unmanned surface vehicles (USV). However, existing methods suffer from poor estimation of the water edge in the presence of visual ambiguities, poor detection of small obstacles and high false-positive rate on water reflections and wakes. We propose a new deep encoder-decoder architecture, a water-obstacle separation and refinement network (WaSR), to address these issues. Detection and water edge accuracy are improved by a novel decoder that gradually fuses inertial information from IMU with the visual features from the encoder. In addition, a novel loss function is designed to increase the separation between water and obstacle features early on in the network. Subsequently, the capacity of the remaining layers in the decoder is better utilised, leading to a significant reduction in false positives and increased true positives. Experimental results show that WaSR outperforms the current state-of-the-art by a large margin, yielding a 14% increase in F-measure over the second-best method.
The prosperity of artificial intelligence has aroused intensive interests in intelligent/autonomous navigation, in which path prediction is a key functionality for decision supports, e.g. route planning, collision warning, and traffic regulation. For maritime intelligence, Automatic Identification System (AIS) plays an important role because it recently has been made compulsory for large international commercial vessels and is able to provide nearly real-time information of the vessel. Therefore AIS data based vessel path prediction is a promising way in future maritime intelligence. However, real-world AIS data collected online are just highly irregular trajectory segments (AIS message sequences) from different types of vessels and geographical regions, with possibly very low data quality. So even there are some works studying how to build a path prediction model using historical AIS data, but still, it is a very challenging problem. In this paper, we propose a comprehensive framework to model massive historical AIS trajectory segments for accurate vessel path prediction. Experimental comparisons with existing popular methods are made to validate the proposed approach and results show that our approach could outperform the baseline methods by a wide margin.
In this work, we propose a new learning approach for autonomous navigation and landing of an Unmanned-Aerial-Vehicle (UAV). We develop a multimodal fusion of deep neural architectures for visual-inertial odometry. We train the model in an end-to-end fashion to estimate the current vehicle pose from streams of visual and inertial measurements. We first evaluate the accuracy of our estimation by comparing the prediction of the model to traditional algorithms on the publicly available EuRoC MAV dataset. The results illustrate a $25 \%$ improvement in estimation accuracy over the baseline. Finally, we integrate the architecture in the closed-loop flight control system of Airsim - a plugin simulator for Unreal Engine - and we provide simulation results for autonomous navigation and landing.
In densely populated environments, socially compliant navigation is critical for autonomous robots as driving close to people is unavoidable. This manner of social navigation is challenging given the constraints of human comfort and social rules. Traditional methods based on hand-craft cost functions to achieve this task have difficulties to operate in the complex real world. Other learning-based approaches fail to address the naturalness aspect from the perspective of collective formation behaviors. We present an autonomous navigation system capable of operating in dense crowds and utilizing information of social groups. The underlying system incorporates a deep neural network to track social groups and join the flow of a social group in facilitating the navigation. A collision avoidance layer in the system further ensures navigation safety. In experiments, our method generates socially compliant behaviors as state-of-the-art methods. More importantly, the system is capable of navigating safely in a densely populated area (10+ people in a 10m x 20m area) following crowd flows to reach the goal.
Long Wave Infrared (LWIR) cameras provide images regardles of the ambient illumination, they tolerate fog and are not blinded by the incoming car headlights. These features make LWIR cameras attractive for autonomous navigation, security and military applications. Thermal images can be used similarly to the visible range ones, including 3D scene reconstruction with two or more such cameras mounted on a rigid frame. There are two additional challenges for this spectral range: lower image resolution and lower contrast of the textures. In this work, we demonstrate quadocular LWIR camera setup, calibration, image capturing and processing that result in long range 3D perception with 0.077 pix disparity error over 90% of the depth map. With low resolution (160 x 120) LWIR sensors we achieved 10% range accuracy at 28 m with 56 degrees horizontal field of view (HFoV) and 150 mm baseline. Scaled to the now-standard 640 x 512 resolution and 200 mm baseline suitable for head-mounted application the result would be 10% accuracy at 130 m.
This paper is a technical report about our submission for the ECCV 2018 3DRMS Workshop Challenge on Semantic 3D Reconstruction \cite{Tylecek2018rms}. In this paper, we address 3D semantic reconstruction for autonomous navigation using co-learning of depth map and semantic segmentation. The core of our pipeline is a deep multi-task neural network which tightly refines depth and also produces accurate semantic segmentation maps. Its inputs are an image and a raw depth map produced from a pair of images by standard stereo vision. The resulting semantic 3D point clouds are then merged in order to create a consistent 3D mesh, in turn used to produce dense semantic 3D reconstruction maps. The performances of each step of the proposed method are evaluated on the dataset and multiple tasks of the 3DRMS Challenge, and repeatedly surpass state-of-the-art approaches.
We present Decentralized Distributed Proximal Policy Optimization (DD-PPO), a method for distributed reinforcement learning in resource-intensive simulated environments. DD-PPO is distributed (uses multiple machines), decentralized (lacks a centralized server), and synchronous (no computation is ever stale), making it conceptually simple and easy to implement. In our experiments on training virtual robots to navigate in Habitat-Sim, DD-PPO exhibits near-linear scaling -- achieving a speedup of 107x on 128 GPUs over a serial implementation. We leverage this scaling to train an agent for 2.5 Billion steps of experience (the equivalent of 80 years of human experience) -- over 6 months of GPU-time training in under 3 days of wall-clock time with 64 GPUs. This massive-scale training not only sets the state of art on Habitat Autonomous Navigation Challenge 2019, but essentially solves the task --near-perfect autonomous navigation in an unseen environment without access to a map, directly from an RGB-D camera and a GPS+Compass sensor. Fortuitously, error vs computation exhibits a power-law-like distribution; thus, 90% of peak performance is obtained relatively early (at 100 million steps) and relatively cheaply (under 1 day with 8 GPUs). Finally, we show that the scene understanding and navigation policies learned can be transferred to other navigation tasks -- the analog of ImageNet pre-training + task-specific fine-tuning for embodied AI. Our model outperforms ImageNet pre-trained CNNs on these transfer tasks and can serve as a universal resource (all models and code are publicly available).
We present JRDB, a novel egocentric dataset collected from our social mobile manipulator JackRabbot. The dataset includes 64 minutes of annotated multimodal sensor data including stereo cylindrical 360$^\circ$ RGB video at 15 fps, 3D point clouds from two Velodyne 16 Lidars, line 3D point clouds from two Sick Lidars, audio signal, RGB-D video at 30 fps, 360$^\circ$ spherical image from a fisheye camera and encoder values from the robot's wheels. Our dataset incorporates data from traditionally underrepresented scenes such as indoor environments and pedestrian areas, all from the ego-perspective of the robot, both stationary and navigating. The dataset has been annotated with over 2.3 million bounding boxes spread over 5 individual cameras and 1.8 million associated 3D cuboids around all people in the scenes totaling over 3500 time consistent trajectories. Together with our dataset and the annotations, we launch a benchmark and metrics for 2D and 3D person detection and tracking. With this dataset, which we plan on extending with further types of annotation in the future, we hope to provide a new source of data and a test-bench for research in the areas of egocentric robot vision, autonomous navigation, and all perceptual tasks around social robotics in human environments.
State-of-the-art algorithms for visual place recognition, and related visual navigation systems, can be broadly split into two categories: computer-science-oriented models including deep learning or image retrieval-based techniques with minimal biological plausibility, and neuroscience-oriented dynamical networks that model temporal properties underlying spatial navigation in the brain. In this letter, we propose a new compact and high-performing place recognition model that bridges this divide for the first time. Our approach comprises two key neural models of these categories: (1) FlyNet, a compact, sparse two-layer neural network inspired by brain architectures of fruit flies, Drosophila melanogaster, and (2) a one-dimensional continuous attractor neural network (CANN). The resulting FlyNet+CANN network incorporates the compact pattern recognition capabilities of our FlyNet model with the powerful temporal filtering capabilities of an equally compact CANN, replicating entirely in a hybrid neural implementation the functionality that yields high performance in algorithmic localization approaches like SeqSLAM. We evaluate our model, and compare it to three state-of-the-art methods, on two benchmark real-world datasets with small viewpoint variations and extreme environmental changes - achieving 87% AUC results under day to night transitions compared to 60% for Multi-Process Fusion, 46% for LoST-X and 1% for SeqSLAM, while being 6.5, 310, and 1.5 times faster, respectively.