arXiv subjects

Abhinav Valada

Publications and source records attributed to Abhinav Valada.

173 records · Page 10Linked to original sources

arXiv2020

Multimodal Interaction-aware Motion Prediction for Autonomous Street Crossing

For mobile robots navigating on sidewalks, it is essential to be able to safely cross street intersections. Most existing approaches rely on the recognition of the traffic light signal to make an informed crossing decision. Although these approaches have been crucial enablers for urban navigation, the capabilities of robots employing such approaches are still limited to navigating only on streets containing signalized intersections. In this paper, we address this challenge and propose a multimodal convolutional neural network framework to predict the safety of a street intersection for crossing. Our architecture consists of two subnetworks; an interaction-aware trajectory estimation stream IA-TCNN, that predicts the future states of all observed traffic participants in the scene, and a traffic light recognition stream AtteNet. Our IA-TCNN utilizes dilated causal convolutions to model the behavior of the observable dynamic agents in the scene without explicitly assigning priorities to the interactions among them. While AtteNet utilizes Squeeze-Excitation blocks to learn a content-aware mechanism for selecting the relevant features from the data, thereby improving the noise robustness. Learned representations from the traffic light recognition stream are fused with the estimated trajectories from the motion prediction stream to learn the crossing decision. Furthermore, we extend our previously introduced Freiburg Street Crossing dataset with sequences captured at different types of intersections, demonstrating complex interactions among the traffic participants. Extensive experimental evaluations on public benchmark datasets and our proposed dataset demonstrate that our network achieves state-of-the-art performance for each of the subtasks, as well as for the crossing safety prediction.

cs.RO↗

arXiv2020

MOPT: Multi-Object Panoptic Tracking

Comprehensive understanding of dynamic scenes is a critical prerequisite for intelligent robots to autonomously operate in their environment. Research in this domain, which encompasses diverse perception problems, has primarily been focused on addressing specific tasks individually rather than modeling the ability to understand dynamic scenes holistically. In this paper, we introduce a novel perception task denoted as multi-object panoptic tracking (MOPT), which unifies the conventionally disjoint tasks of semantic segmentation, instance segmentation, and multi-object tracking. MOPT allows for exploiting pixel-level semantic information of 'thing' and 'stuff' classes, temporal coherence, and pixel-level associations over time, for the mutual benefit of each of the individual sub-problems. To facilitate quantitative evaluations of MOPT in a unified manner, we propose the soft panoptic tracking quality (sPTQ) metric. As a first step towards addressing this task, we propose the novel PanopticTrackNet architecture that builds upon the state-of-the-art top-down panoptic segmentation network EfficientPS by adding a new tracking head to simultaneously learn all sub-tasks in an end-to-end manner. Additionally, we present several strong baselines that combine predictions from state-of-the-art panoptic segmentation and multi-object tracking models for comparison. We present extensive quantitative and qualitative evaluations of both vision-based and LiDAR-based MOPT that demonstrate encouraging results.

cs.CV↗

arXiv2020

CMRNet++: Map and Camera Agnostic Monocular Visual Localization in LiDAR Maps

Localization is a critically essential and crucial enabler of autonomous robots. While deep learning has made significant strides in many computer vision tasks, it is still yet to make a sizeable impact on improving capabilities of metric visual localization. One of the major hindrances has been the inability of existing Convolutional Neural Network (CNN)-based pose regression methods to generalize to previously unseen places. Our recently introduced CMRNet effectively addresses this limitation by enabling map independent monocular localization in LiDAR-maps. In this paper, we now take it a step further by introducing CMRNet++, which is a significantly more robust model that not only generalizes to new places effectively, but is also independent of the camera parameters. We enable this capability by combining deep learning with geometric techniques, and by moving the metric reasoning outside the learning process. In this way, the weights of the network are not tied to a specific camera. Extensive evaluations of CMRNet++ on three challenging autonomous driving datasets, i.e., KITTI, Argoverse, and Lyft5, show that CMRNet++ outperforms CMRNet as well as other baselines by a large margin. More importantly, for the first-time, we demonstrate the ability of a deep learning approach to accurately localize without any retraining or fine-tuning in a completely new environment and independent of the camera parameters.

cs.CV↗

arXiv2019

Self-Supervised Visual Terrain Classification from Unsupervised Acoustic Feature Learning

Mobile robots operating in unknown urban environments encounter a wide range of complex terrains to which they must adapt their planned trajectory for safe and efficient navigation. Most existing approaches utilize supervised learning to classify terrains from either an exteroceptive or a proprioceptive sensor modality. However, this requires a tremendous amount of manual labeling effort for each newly encountered terrain as well as for variations of terrains caused by changing environmental conditions. In this work, we propose a novel terrain classification framework leveraging an unsupervised proprioceptive classifier that learns from vehicle-terrain interaction sounds to self-supervise an exteroceptive classifier for pixel-wise semantic segmentation of images. To this end, we first learn a discriminative embedding space for vehicle-terrain interaction sounds from triplets of audio clips formed using visual features of the corresponding terrain patches and cluster the resulting embeddings. We subsequently use these clusters to label the visual terrain patches by projecting the traversed tracks of the robot into the camera images. Finally, we use the sparsely labeled images to train our semantic segmentation network in a weakly supervised manner. We present extensive quantitative and qualitative results that demonstrate that our proprioceptive terrain classifier exceeds the state-of-the-art among unsupervised methods and our self-supervised exteroceptive semantic segmentation model achieves a comparable performance to supervised learning with manually labeled data.

cs.RO↗

arXiv2019

Vision-Based Autonomous UAV Navigation and Landing for Urban Search and Rescue

Unmanned Aerial Vehicles (UAVs) equipped with bioradars are a life-saving technology that can enable identification of survivors under collapsed buildings in the aftermath of natural disasters such as earthquakes or gas explosions. However, these UAVs have to be able to autonomously navigate in disaster struck environments and land on debris piles in order to accurately locate the survivors. This problem is extremely challenging as pre-existing maps cannot be leveraged for navigation due to structural changes that may have occurred. Furthermore, existing landing site detection algorithms are not suitable to identify safe landing regions on debris piles. In this work, we present a computationally efficient system for autonomous UAV navigation and landing that does not require any prior knowledge about the environment. We propose a novel landing site detection algorithm that computes costmaps based on several hazard factors including terrain flatness, steepness, depth accuracy, and energy consumption information. We also introduce a first-of-a-kind synthetic dataset of over 1.2 million images of collapsed buildings with groundtruth depth, surface normals, semantics and camera pose information. We demonstrate the efficacy of our system using experiments from a city scale hyperrealistic simulation environment and in real-world scenarios with collapsed buildings.

cs.RO↗

arXiv2019

Robot Localization in Floor Plans Using a Room Layout Edge Extraction Network

Indoor localization is one of the crucial enablers for deployment of service robots. Although several successful techniques for indoor localization have been proposed, the majority of them relies on maps generated from data gathered with the same sensor modality used for localization. Typically, tedious labor by experts is needed to acquire this data, thus limiting the readiness of the system as well as its ease of installation for inexperienced operators. In this paper, we propose a memory and computationally efficient monocular camera-based localization system that allows a robot to estimate its pose given an architectural floor plan. Our method employs a convolutional neural network to predict room layout edges from a single camera image and estimates the robot pose using a particle filter that matches the extracted edges to the given floor plan. We evaluate our localization system using multiple real-world experiments and demonstrate that it has the robustness and accuracy required for reliable indoor navigation.

cs.RO↗

arXiv2019

Self-Supervised Model Adaptation for Multimodal Semantic Segmentation

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by varying illumination and weather conditions. Leveraging complementary modalities can enable learning of semantically richer representations that are resilient to such perturbations. Despite the tremendous progress in recent years, most multimodal convolutional neural network approaches directly concatenate feature maps from individual modality streams rendering the model incapable of focusing only on relevant complementary information for fusion. To address this limitation, we propose a mutimodal semantic segmentation framework that dynamically adapts the fusion of modality-specific features while being sensitive to the object category, spatial location and scene context in a self-supervised manner. Specifically, we propose an architecture consisting of two modality-specific encoder streams that fuse intermediate encoder representations into a single decoder using our proposed self-supervised model adaptation fusion mechanism which optimally combines complementary features. As intermediate representations are not aligned across modalities, we introduce an attention scheme for better correlation. In addition, we propose a computationally efficient unimodal segmentation architecture termed AdapNet++ that incorporates a new encoder with multiscale residual units and an efficient atrous spatial pyramid pooling that has a larger effective receptive field with more than 10x fewer parameters, complemented with a strong decoder with a multi-resolution supervision scheme that recovers high-resolution details. Comprehensive empirical evaluations on several benchmarks demonstrate that both our unimodal and multimodal architectures achieve state-of-the-art performance.

cs.CV↗

arXiv2018

VLocNet++: Deep Multitask Learning for Semantic Visual Localization and Odometry

Semantic understanding and localization are fundamental enablers of robot autonomy that have for the most part been tackled as disjoint problems. While deep learning has enabled recent breakthroughs across a wide spectrum of scene understanding tasks, its applicability to state estimation tasks has been limited due to the direct formulation that renders it incapable of encoding scene-specific constrains. In this work, we propose the VLocNet++ architecture that employs a multitask learning approach to exploit the inter-task relationship between learning semantics, regressing 6-DoF global pose and odometry, for the mutual benefit of each of these tasks. Our network overcomes the aforementioned limitation by simultaneously embedding geometric and semantic knowledge of the world into the pose regression network. We propose a novel adaptive weighted fusion layer to aggregate motion-specific temporal information and to fuse semantic features into the localization stream based on region activations. Furthermore, we propose a self-supervised warping technique that uses the relative motion to warp intermediate network representations in the segmentation stream for learning consistent semantics. Finally, we introduce a first-of-a-kind urban outdoor localization dataset with pixel-level semantic labels and multiple loops for training deep networks. Extensive experiments on the challenging Microsoft 7-Scenes benchmark and our DeepLoc dataset demonstrate that our approach exceeds the state-of-the-art outperforming local feature-based methods while simultaneously performing multiple tasks and exhibiting substantial robustness in challenging scenarios.

cs.RO↗

arXiv2018

Vision-based Autonomous Landing in Catastrophe-Struck Environments

Unmanned Aerial Vehicles (UAVs) equipped with bioradars are a life-saving technology that can enable identification of survivors under collapsed buildings in the aftermath of natural disasters such as earthquakes or gas explosions. However, these UAVs have to be able to autonomously land on debris piles in order to accurately locate the survivors. This problem is extremely challenging as the structure of these debris piles is often unknown and no prior knowledge can be leveraged. In this work, we propose a computationally efficient system that is able to reliably identify safe landing sites and autonomously perform the landing maneuver. Specifically, our algorithm computes costmaps based on several hazard factors including terrain flatness, steepness, depth accuracy and energy consumption information. We first estimate dense candidate landing sites from the resulting costmap and then employ clustering to group neighboring sites into a safe landing region. Finally, a minimum-jerk trajectory is computed for landing considering the surrounding obstacles and the UAV dynamics. We demonstrate the efficacy of our system using experiments from a city scale hyperrealistic simulation environment and in real-world scenarios with collapsed buildings.

cs.RO↗

arXiv2018

Deep Spatiotemporal Models for Robust Proprioceptive Terrain Classification

Terrain classification is a critical component of any autonomous mobile robot system operating in unknown real-world environments. Over the years, several proprioceptive terrain classification techniques have been introduced to increase robustness or act as a fallback for traditional vision based approaches. However, they lack widespread adaptation due to various factors that include inadequate accuracy, robustness and slow run-times. In this paper, we use vehicle-terrain interaction sounds as a proprioceptive modality and propose a deep Long-Short Term Memory (LSTM) based recurrent model that captures both the spatial and temporal dynamics of such a problem, thereby overcoming these past limitations. Our model consists of a new Convolution Neural Network (CNN) architecture that learns deep spatial features, complemented with LSTM units that learn complex temporal dynamics. Experiments on two extensive datasets collected with different microphones on various indoor and outdoor terrains demonstrate state-of-the-art performance compared to existing techniques. We additionally evaluate the performance in adverse acoustic conditions with high ambient noise and propose a noise-aware training scheme that enables learning of more generalizable models that are essential for robust real-world deployments.

cs.RO↗

arXiv2018

Deep Auxiliary Learning for Visual Localization and Odometry

Localization is an indispensable component of a robot's autonomy stack that enables it to determine where it is in the environment, essentially making it a precursor for any action execution or planning. Although convolutional neural networks have shown promising results for visual localization, they are still grossly outperformed by state-of-the-art local feature-based techniques. In this work, we propose VLocNet, a new convolutional neural network architecture for 6-DoF global pose regression and odometry estimation from consecutive monocular images. Our multitask model incorporates hard parameter sharing, thus being compact and enabling real-time inference, in addition to being end-to-end trainable. We propose a novel loss function that utilizes auxiliary learning to leverage relative pose information during training, thereby constraining the search space to obtain consistent pose estimates. We evaluate our proposed VLocNet on indoor as well as outdoor datasets and show that even our single task model exceeds the performance of state-of-the-art deep architectures for global localization, while achieving competitive performance for visual odometry estimation. Furthermore, we present extensive experimental evaluations utilizing our proposed Geometric Consistency Loss that show the effectiveness of multitask learning and demonstrate that our model is the first deep learning technique to be on par with, and in some cases outperforms state-of-the-art SIFT-based approaches.

cs.RO↗