arXiv subjects

Mark Campbell

Publications and source records attributed to Mark Campbell.

At least 55 records · Page 3Linked to original sources

arXiv2021

Mixed-Integer Linear Programming Models for Multi-Robot Non-Adversarial Search

In this letter, we consider the Multi-Robot Efficient Search Path Planning (MESPP) problem, where a team of robots is deployed in a graph-represented environment to capture a moving target within a given deadline. We prove this problem to be NP-hard, and present the first set of Mixed-Integer Linear Programming (MILP) models to tackle the MESPP problem. Our models are the first to encompass multiple searchers, arbitrary capture ranges, and false negatives simultaneously. While state-of-the-art algorithms for MESPP are based on simple path enumeration, the adoption of MILP as a planning paradigm allows to leverage the powerful techniques of modern solvers, yielding better computational performance and, as a consequence, longer planning horizons. The models are designed for computing optimal solutions offline, but can be easily adapted for a distributed online approach. Our simulations show that it is possible to achieve 98% decrease in computational time relative to the previous state-of-the-art. We also show that the distributed approach performs nearly as well as the centralized, within 6% in the settings studied in this letter, with the advantage of requiring significant less time - an important consideration in practical search missions.

cs.RO↗

arXiv2020

Planning Paths Through Unknown Space by Imagining What Lies Therein

This paper presents a novel framework for planning paths in maps containing unknown spaces, such as from occlusions. Our approach takes as input a semantically-annotated point cloud, and leverages an image inpainting neural network to generate a reasonable model of unknown space as free or occupied. Our validation campaign shows that it is possible to greatly increase the performance of standard pathfinding algorithms which adopt the general optimistic assumption of treating unknown space as free.

cs.RO↗

arXiv2020

Train in Germany, Test in The USA: Making 3D Object Detectors Generalize

In the domain of autonomous driving, deep learning has substantially improved the 3D object detection accuracy for LiDAR and stereo camera data alike. While deep networks are great at generalization, they are also notorious to over-fit to all kinds of spurious artifacts, such as brightness, car sizes and models, that may appear consistently throughout the data. In fact, most datasets for autonomous driving are collected within a narrow subset of cities within one country, typically under similar weather conditions. In this paper we consider the task of adapting 3D object detectors from one dataset to another. We observe that naively, this appears to be a very challenging task, resulting in drastic drops in accuracy levels. We provide extensive experiments to investigate the true adaptation challenges and arrive at a surprising conclusion: the primary adaptation hurdle to overcome are differences in car sizes across geographic areas. A simple correction based on the average car size yields a strong correction of the adaptation gap. Our proposed method is simple and easily incorporated into most 3D object detection frameworks. It provides a first baseline for 3D object detection adaptation across countries, and gives hope that the underlying problem may be more within grasp than one may have hoped to believe. Our code is available at https://github.com/cxy1997/3D_adapt_auto_driving.

cs.CV↗

arXiv2020

End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection

Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings. Recently, the introduction of pseudo-LiDAR (PL) has led to a drastic reduction in the accuracy gap between methods based on LiDAR sensors and those based on cheap stereo cameras. PL combines state-of-the-art deep neural networks for 3D depth estimation with those for 3D object detection by converting 2D depth map outputs to 3D point cloud inputs. However, so far these two networks have to be trained separately. In this paper, we introduce a new framework based on differentiable Change of Representation (CoR) modules that allow the entire PL pipeline to be trained end-to-end. The resulting framework is compatible with most state-of-the-art networks for both tasks and in combination with PointRCNN improves over PL consistently across all benchmarks -- yielding the highest entry on the KITTI image-based 3D object detection leaderboard at the time of submission. Our code will be made available at https://github.com/mileyan/pseudo-LiDAR_e2e.

cs.CV↗

arXiv2020

DeepSemanticHPPC: Hypothesis-based Planning over Uncertain Semantic Point Clouds

Planning in unstructured environments is challenging -- it relies on sensing, perception, scene reconstruction, and reasoning about various uncertainties. We propose DeepSemanticHPPC, a novel uncertainty-aware hypothesis-based planner for unstructured environments. Our algorithmic pipeline consists of: a deep Bayesian neural network which segments surfaces with uncertainty estimates; a flexible point cloud scene representation; a next-best-view planner which minimizes the uncertainty of scene semantics using sparse visual measurements; and a hypothesis-based path planner that proposes multiple kinematically feasible paths with evolving safety confidences given next-best-view measurements. Our pipeline iteratively decreases semantic uncertainty along planned paths, filtering out unsafe paths with high confidence. We show that our framework plans safe paths in real-world environments where existing path planners typically fail.

cs.RO↗

arXiv2020

Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving

3D object detection is an essential task in autonomous driving. Recent techniques excel with highly accurate detection rates, provided the 3D input data is obtained from precise but expensive LiDAR technology. Approaches based on cheaper monocular or stereo imagery data have, until now, resulted in drastically lower accuracies --- a gap that is commonly attributed to poor image-based depth estimation. However, in this paper we argue that it is not the quality of the data but its representation that accounts for the majority of the difference. Taking the inner workings of convolutional neural networks into consideration, we propose to convert image-based depth maps to pseudo-LiDAR representations --- essentially mimicking the LiDAR signal. With this representation we can apply different existing LiDAR-based detection algorithms. On the popular KITTI benchmark, our approach achieves impressive improvements over the existing state-of-the-art in image-based performance --- raising the detection accuracy of objects within the 30m range from the previous state-of-the-art of 22% to an unprecedented 74%. At the time of submission our algorithm holds the highest entry on the KITTI 3D object detection leaderboard for stereo-image-based approaches. Our code is publicly available at https://github.com/mileyan/pseudo_lidar.

cs.CV↗

arXiv2020

Interactive Natural Language-based Person Search

In this work, we consider the problem of searching people in an unconstrained environment, with natural language descriptions. Specifically, we study how to systematically design an algorithm to effectively acquire descriptions from humans. An algorithm is proposed by adapting models, used for visual and language understanding, to search a person of interest (POI) in a principled way, achieving promising results without the need to re-design another complicated model. We then investigate an iterative question-answering (QA) strategy that enable robots to request additional information about the POI's appearance from the user. To this end, we introduce a greedy algorithm to rank questions in terms of their significance, and equip the algorithm with the capability to dynamically adjust the length of human-robot interaction according to model's uncertainty. Our approach is validated not only on benchmark datasets but on a mobile robot, moving in a dynamic and crowded environment.

cs.RO↗

arXiv2020

Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving

Detecting objects such as cars and pedestrians in 3D plays an indispensable role in autonomous driving. Existing approaches largely rely on expensive LiDAR sensors for accurate depth information. While recently pseudo-LiDAR has been introduced as a promising alternative, at a much lower cost based solely on stereo images, there is still a notable performance gap. In this paper we provide substantial advances to the pseudo-LiDAR framework through improvements in stereo depth estimation. Concretely, we adapt the stereo network architecture and loss function to be more aligned with accurate depth estimation of faraway objects --- currently the primary weakness of pseudo-LiDAR. Further, we explore the idea to leverage cheaper but extremely sparse LiDAR sensors, which alone provide insufficient information for 3D detection, to de-bias our depth estimation. We propose a depth-propagation algorithm, guided by the initial depth estimates, to diffuse these few exact measurements across the entire depth map. We show on the KITTI object detection benchmark that our combined approach yields substantial improvements in depth estimation and stereo-based 3D object detection --- outperforming the previous state-of-the-art detection accuracy for faraway objects by 40%. Our code is available at https://github.com/mileyan/Pseudo_Lidar_V2.

cs.CV↗

arXiv2020

Revisiting Meta-Learning as Supervised Learning

Recent years have witnessed an abundance of new publications and approaches on meta-learning. This community-wide enthusiasm has sparked great insights but has also created a plethora of seemingly different frameworks, which can be hard to compare and evaluate. In this paper, we aim to provide a principled, unifying framework by revisiting and strengthening the connection between meta-learning and traditional supervised learning. By treating pairs of task-specific data sets and target models as (feature, label) samples, we can reduce many meta-learning algorithms to instances of supervised learning. This view not only unifies meta-learning into an intuitive and practical framework but also allows us to transfer insights from supervised learning directly to improve meta-learning. For example, we obtain a better understanding of generalization properties, and we can readily transfer well-understood techniques, such as model ensemble, pre-training, joint training, data augmentation, and even nearest neighbor based methods. We provide an intuitive analogy of these methods in the context of meta-learning and show that they give rise to significant improvements in model performance on few-shot learning.

cs.LG↗

arXiv2020

Pedestrian Motion Model Using Non-Parametric Trajectory Clustering and Discrete Transition Points

This paper presents a pedestrian motion model that includes both low level trajectory patterns, and high level discrete transitions. The inclusion of both levels creates a more general predictive model, allowing for more meaningful prediction and reasoning about pedestrian trajectories, as compared to the current state of the art. The model uses an iterative clustering algorithm with (1) Dirichlet Process Gaussian Processes to cluster trajectories into continuous motion patterns and (2) hypothesis testing to identify discrete transitions in the data called transition points. The model iteratively splits full trajectories into sub-trajectory clusters based on transition points, where pedestrians make discrete decisions. State transition probabilities are then learned over the transition points and trajectory clusters. The model is for online prediction of motions, and detection of anomalous trajectories. The proposed model is validated on the Duke MTMC dataset to demonstrate identification of low level trajectory clusters and high level transitions, and the ability to predict pedestrian motion and detect anomalies online with high accuracy.

cs.RO↗

arXiv2020

An Empirical Study of Person Re-Identification with Attributes

Person re-identification aims to identify a person from an image collection, given one image of that person as the query. There is, however, a plethora of real-life scenarios where we may not have a priori library of query images and therefore must rely on information from other modalities. In this paper, an attribute-based approach is proposed where the person of interest (POI) is described by a set of visual attributes, which are used to perform the search. We compare multiple algorithms and analyze how the quality of attributes impacts the performance. While prior work mostly relies on high precision attributes annotated by experts, we conduct a human-subject study and reveal that certain visual attributes could not be consistently described by human observers, making them less reliable in real applications. A key conclusion is that the performance achieved by non-expert attributes, instead of expert-annotated ones, is a more faithful indicator of the status quo of attribute-based approaches for person re-identification.

cs.CV↗

arXiv2019

LDLS: 3-D Object Segmentation Through Label Diffusion From 2-D Images

Object segmentation in three-dimensional (3-D) point clouds is a critical task for robots capable of 3-D perception. Despite the impressive performance of deep learning-based approaches on object segmentation in 2-D images, deep learning has not been applied nearly as successfully for 3-D point cloud segmentation. Deep networks generally require large amounts of labeled training data, which are readily available for 2-D images but are difficult to produce for 3-D point clouds. In this letter, we present Label Diffusion Lidar Segmentation (LDLS), a novel approach for 3-D point cloud segmentation, which leverages 2-D segmentation of an RGB image from an aligned camera to avoid the need for training on annotated 3-D data. We obtain 2-D segmentation predictions by applying Mask-RCNN to the RGB image, and then link this image to a 3-D lidar point cloud by building a graph of connections among 3-D points and 2-D pixels. This graph then directs a semi-supervised label diffusion process, where the 2-D pixels act as source nodes that diffuse object label information through the 3-D point cloud, resulting in a complete 3-D point cloud segmentation. We conduct empirical studies on the KITTI benchmark dataset and on a mobile robot, demonstrating wide applicability and superior performance of LDLS compared with the previous state of the art in 3-D point cloud segmentation, without any need for either 3-D training data or fine tuning of the 2-D image segmentation model.

eess.IV↗

arXiv2019

Anytime Stereo Image Depth Estimation on Mobile Devices

Many applications of stereo depth estimation in robotics require the generation of accurate disparity maps in real time under significant computational constraints. Current state-of-the-art algorithms force a choice between either generating accurate mappings at a slow pace, or quickly generating inaccurate ones, and additionally these methods typically require far too many parameters to be usable on power- or memory-constrained devices. Motivated by these shortcomings, we propose a novel approach for disparity prediction in the anytime setting. In contrast to prior work, our end-to-end learned approach can trade off computation and accuracy at inference time. Depth estimation is performed in stages, during which the model can be queried at any time to output its current best estimate. Our final model can process 1242$ \times $375 resolution images within a range of 10-35 FPS on an NVIDIA Jetson TX2 module with only marginal increases in error -- using two orders of magnitude fewer parameters than the most competitive baseline. The source code is available at https://github.com/mileyan/AnyNet .

cs.CV↗

arXiv2018

An Integrated System for Perception-Driven Autonomy with Modular Robots

The theoretical ability of modular robots to reconfigure in response to complex tasks in a priori unknown environments has frequently been cited as an advantage and remains a major motivator for work in the field. We present a modular robot system capable of autonomously completing high-level tasks by reactively reconfiguring to meet the needs of a perceived, a priori unknown environment. The system integrates perception, high-level planning, and modular hardware, and is validated in three hardware demonstrations. Given a high-level task specification, a modular robot autonomously explores an unknown environment, decides when and how to reconfigure, and manipulates objects to complete its task. The system architecture balances distributed mechanical elements with centralized perception, planning, and control. By providing an example of how a modular robot system can be designed to leverage reactive reconfigurability in unknown environments, we have begun to lay the groundwork for modular self-reconfigurable robots to address tasks in the real world.

cs.RO↗

arXiv2018

Deep Person Re-identification for Probabilistic Data Association in Multiple Pedestrian Tracking

We present a data association method for vision-based multiple pedestrian tracking, using deep convolutional features to distinguish between different people based on their appearances. These re-identification (re-ID) features are learned such that they are invariant to transformations such as rotation, translation, and changes in the background, allowing consistent identification of a pedestrian moving through a scene. We incorporate re-ID features into a general data association likelihood model for multiple person tracking, experimentally validate this model by using it to perform tracking in two evaluation video sequences, and examine the performance improvements gained as compared to several baseline approaches. Our results demonstrate that using deep person re-ID for data association greatly improves tracking robustness to challenges such as occlusions and path crossings.

cs.CV↗

arXiv2018

Autonomous Urban Localization and Navigation with Limited Information

Urban environments offer a challenging scenario for autonomous driving. Globally localizing information, such as a GPS signal, can be unreliable due to signal shadowing and multipath errors. Detailed a priori maps of the environment with sufficient information for autonomous navigation typically require driving the area multiple times to collect large amounts of data, substantial post-processing on that data to obtain the map, and then maintaining updates on the map as the environment changes. This paper addresses the issue of autonomous driving in an urban environment by investigating algorithms and an architecture to enable fully functional autonomous driving with limited information. An algorithm to autonomously navigate urban roadways with little to no reliance on an a priori map or GPS is developed. Localization is performed with an extended Kalman filter with odometry, compass, and sparse landmark measurement updates. Navigation is accomplished by a compass-based navigation control law. Key results from Monte Carlo studies show success rates of urban navigation under different environmental conditions. Experiments validate the simulated results and demonstrate that, for given test conditions, an expected range can be found for a given success rate.

cs.RO↗

arXiv2018

Secure Minimum Time Planning Under Environmental Uncertainty: an Extended Treatment

Cyber Physical Systems (CPS) are becoming ubiquitous and affect the physical world, yet security is seldom at the forefront of their design. This is especially true of robotic control algorithms which seldom consider the effect of a cyber attack on mission objectives and success. This work presents a secure optimal control algorithm in the face of a cyber attack on a robot's knowledge of the environment. This work focuses on cyber attack, but the results generalize to incomplete or outdated information of an environment. This work fuses ideas from robust control, optimal control, and sensor based planning to provide a generalization of stopping distance in 3D. The planner is implemented in simulation and its properties are analyzed.

cs.RO↗

arXiv2018

Perception-Informed Autonomous Environment Augmentation With Modular Robots

We present a system enabling a modular robot to autonomously build structures in order to accomplish high-level tasks. Building structures allows the robot to surmount large obstacles, expanding the set of tasks it can perform. This addresses a common weakness of modular robot systems, which often struggle to traverse large obstacles. This paper presents the hardware, perception, and planning tools that comprise our system. An environment characterization algorithm identifies features in the environment that can be augmented to create a path between two disconnected regions of the environment. Specially-designed building blocks enable the robot to create structures that can augment the environment to make obstacles traversable. A high-level planner reasons about the task, robot locomotion capabilities, and environment to decide if and where to augment the environment in order to perform the desired task. We validate our system in hardware experiments

cs.RO↗