arXiv subjects

Alois Knoll

Publications and source records attributed to Alois Knoll.

At least 253 records · Page 14Linked to original sources

arXiv2020

Modeling and Testing Multi-Agent Traffic Rules within Interactive Behavior Planning

Autonomous vehicles need to abide by the same rules that humans follow. Some of these traffic rules may depend on multiple agents or time. Especially in situations with traffic participants that interact densely, the interactions with other agents need to be accounted for during planning. To study how multi-agent and time-dependent traffic rules shall be modeled, a framework is needed that restricts the behavior to rule-conformant actions during planning, and that can eventually evaluate the satisfaction of these rules. This work presents a method to model the conformance to traffic rules for interactive behavior planning and to test the ramifications of the traffic rule formulations on metrics such as collision, progress, or rule violations. The interactive behavior planning problem is formulated as a dynamic game and solved using Monte Carlo Tree Search, for which we contribute a new method to integrate history-dependent traffic rules into a decision tree. To study the effect of the rules, we treat it as a multi-objective problem and apply a relaxed lexicographical ordering to the vectorized rewards. We demonstrate our approach in a merging scenario. We evaluate the effect of modeling and combining traffic rules to the eventual compliance in simulation. We show that with our approach, interactive behavior planning while satisfying even complex traffic rules can be achieved. Moving forward, this gives us a generic framework to formalize traffic rules for autonomous vehicles.

cs.RO↗

arXiv2020

Formalizing Traffic Rules for Machine Interpretability

Autonomous vehicles need to be designed to abide by the same rules that humans follow. This is challenging, because traffic rules are fuzzy and not well defined, making them incomprehensible to machines. Satisfaction cannot be incorporated in a planning component without proper formalization, nor can it be monitored and verified during simulation or testing. However, no research work has provided a consistent set of machine-interpretable traffic rules for a given operational driving domain. In this paper, we propose a methodology for the legal study and formalization of traffic rules in a formal language. We use Linear Temporal Logic as a formal specification language to describe temporal behaviors, capable of capturing a wide range of traffic rules. We contribute a formalized set of traffic rules for dual carriageways and evaluate the effectiveness of our formalized rules on a public dataset.

cs.RO↗

arXiv2020

Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation

Reinforcement learning algorithms such as hindsight experience replay (HER) and hindsight goal generation (HGG) have been able to solve challenging robotic manipulation tasks in multi-goal settings with sparse rewards. HER achieves its training success through hindsight replays of past experience with heuristic goals, but under-performs in challenging tasks in which goals are difficult to explore. HGG enhances HER by selecting intermediate goals that are easy to achieve in the short term and promising to lead to target goals in the long term. This guided exploration makes HGG applicable to tasks in which target goals are far away from the object's initial position. However, HGG is not applicable to manipulation tasks with obstacles because the euclidean metric used for HGG is not an accurate distance metric in such environments. In this paper, we propose graph-based hindsight goal generation (G-HGG), an extension of HGG selecting hindsight goals based on shortest distances in an obstacle-avoiding graph, which is a discrete representation of the environment. We evaluated G-HGG on four challenging manipulation tasks with obstacles, where significant enhancements in both sample efficiency and overall success rate are shown over HGG and HER. Videos can be viewed at https://sites.google.com/view/demos-g-hgg/.

cs.RO↗

arXiv2020

Robust Stochastic Bayesian Games for Behavior Space Coverage

A key challenge in multi-agent systems is the design of intelligent agents solving real-world tasks in close interaction with other agents (e.g. humans), thereby being confronted with a variety of behavioral variations and limited knowledge about the true behaviors of observed agents. The practicability of existing works addressing this challenge is being limited due to using finite sets of hypothesis for behavior prediction, the lack of a hypothesis design process ensuring coverage over all behavioral variations and sample-inefficiency when modeling continuous behavioral variations. In this work, we present an approach to this challenge based on a new framework of Robust Stochastic Bayesian Games (RSBGs). An RSBG defines hypothesis sets by partitioning the physically feasible, continuous behavior space of the other agents. It combines the optimality criteria of the Robust Markov Decision Process (RMDP) and the Stochastic Bayesian Game (SBG) to exponentially reduce the sample complexity for planning with hypothesis sets defined over continuous behavior spaces. Our approach outperforms the baseline algorithms in two experiments modeling time-varying intents and large multidimensional behavior spaces, while achieving the same performance as a planner with knowledge of the true behaviors of other agents.

cs.MA↗

arXiv2020

AerialMPTNet: Multi-Pedestrian Tracking in Aerial Imagery Using Temporal and Graphical Features

Multi-pedestrian tracking in aerial imagery has several applications such as large-scale event monitoring, disaster management, search-and-rescue missions, and as input into predictive crowd dynamic models. Due to the challenges such as the large number and the tiny size of the pedestrians (e.g., 4 x 4 pixels) with their similar appearances as well as different scales and atmospheric conditions of the images with their extremely low frame rates (e.g., 2 fps), current state-of-the-art algorithms including the deep learning-based ones are unable to perform well. In this paper, we propose AerialMPTNet, a novel approach for multi-pedestrian tracking in geo-referenced aerial imagery by fusing appearance features from a Siamese Neural Network, movement predictions from a Long Short-Term Memory, and pedestrian interconnections from a GraphCNN. In addition, to address the lack of diverse aerial pedestrian tracking datasets, we introduce the Aerial Multi-Pedestrian Tracking (AerialMPT) dataset consisting of 307 frames and 44,740 pedestrians annotated. We believe that AerialMPT is the largest and most diverse dataset to this date and will be released publicly. We evaluate AerialMPTNet on AerialMPT and KIT AIS, and benchmark with several state-of-the-art tracking methods. Results indicate that AerialMPTNet significantly outperforms other methods on accuracy and time-efficiency.

cs.CV↗

arXiv2020

Graph Neural Networks and Reinforcement Learning for Behavior Generation in Semantic Environments

Most reinforcement learning approaches used in behavior generation utilize vectorial information as input. However, this requires the network to have a pre-defined input-size -- in semantic environments this means assuming the maximum number of vehicles. Additionally, this vectorial representation is not invariant to the order and number of vehicles. To mitigate the above-stated disadvantages, we propose combining graph neural networks with actor-critic reinforcement learning. As graph neural networks apply the same network to every vehicle and aggregate incoming edge information, they are invariant to the number and order of vehicles. This makes them ideal candidates to be used as networks in semantic environments -- environments consisting of objects lists. Graph neural networks exhibit some other advantages that make them favorable to be used in semantic environments. The relational information is explicitly given and does not have to be inferred. Moreover, graph neural networks propagate information through the network and can gather higher-degree information. We demonstrate our approach using a highway lane-change scenario and compare the performance of graph neural networks to conventional ones. We show that graph neural networks are capable of handling scenarios with a varying number and order of vehicles during training and application.

cs.LG↗

arXiv2020

Center-of-Mass-based Robust Grasp Planning for Unknown Objects Using Tactile-Visual Sensors

An unstable grasp pose can lead to slip, thus an unstable grasp pose can be predicted by slip detection. A regrasp is required afterwards to correct the grasp pose in order to finish the task. In this work, we propose a novel regrasp planner with multi-sensor modules to plan grasp adjustments with the feedback from a slip detector. Then a regrasp planner is trained to estimate the location of center of mass, which helps robots find an optimal grasp pose. The dataset in this work consists of 1 025 slip experiments and 1 347 regrasps collected by one pair of tactile sensors, an RGB-D camera and one Franka Emika robot arm equipped with joint force/torque sensors. We show that our algorithm can successfully detect and classify the slip for 5 unknown test objects with an accuracy of 76.88% and a regrasp planner increases the grasp success rate by 31.0% compared to the state-of-the-art vision-based grasping algorithm.

cs.RO↗

arXiv2020

Globally optimal vertical direction estimation in Atlanta World

In man-made environments, such as indoor and urban scenes, most of the objects and structures are organized in the form of orthogonal and parallel planes. These planes can be approximated by the Atlanta world assumption, in which the normals of planes can be represented by the Atlanta frames. Atlanta world assumption, which can be considered as a generalized Manhattan world assumption, has one vertical frame and multiple horizontal frames. Conventionally, given a set of inputs such as surface normals, the Atlanta frame estimation problem can be solved in one-time by branch-and-bound (BnB). However, the runtime of the BnB algorithm will increase greatly when the dimensionality (i.e., the number of horizontal frames) increases. In this paper, we estimate only the vertical direction instead of all Atlanta frames at once. Accordingly, we propose a vertical direction estimation method by considering the relationship between the vertical frame and horizontal frames. Concretely, our approach employs a BnB algorithm to search the vertical direction guaranteeing global optimality without requiring prior knowledge of the number of Atlanta frames. Four novel bounds by mapping 3D-hemisphere to a 2D region are investigated to guarantee convergence. We verify the validity of the proposed method in various challenging synthetic and real-world data.

cs.CV↗

arXiv2020

Task-Independent Spiking Central Pattern Generator: A Learning-Based Approach

Legged locomotion is a challenging task in the field of robotics but a rather simple one in nature. This motivates the use of biological methodologies as solutions to this problem. Central pattern generators are neural networks that are thought to be responsible for locomotion in humans and some animal species. As for robotics, many attempts were made to reproduce such systems and use them for a similar goal. One interesting design model is based on spiking neural networks. This model is the main focus of this work, as its contribution is not limited to engineering but also applicable to neuroscience. This paper introduces a new general framework for building central pattern generators that are task-independent, biologically plausible, and rely on learning methods. The abilities and properties of the presented approach are not only evaluated in simulation but also in a robotic experiment. The results are very promising as the used robot was able to perform stable walking at different speeds and to change speed within the same gait cycle.

cs.NE↗

arXiv2020

Indirect and Direct Training of Spiking Neural Networks for End-to-End Control of a Lane-Keeping Vehicle

Building spiking neural networks (SNNs) based on biological synaptic plasticities holds a promising potential for accomplishing fast and energy-efficient computing, which is beneficial to mobile robotic applications. However, the implementations of SNNs in robotic fields are limited due to the lack of practical training methods. In this paper, we therefore introduce both indirect and direct end-to-end training methods of SNNs for a lane-keeping vehicle. First, we adopt a policy learned using the \textcolor{black}{Deep Q-Learning} (DQN) algorithm and then subsequently transfer it to an SNN using supervised learning. Second, we adopt the reward-modulated spike-timing-dependent plasticity (R-STDP) for training SNNs directly, since it combines the advantages of both reinforcement learning and the well-known spike-timing-dependent plasticity (STDP). We examine the proposed approaches in three scenarios in which a robot is controlled to keep within lane markings by using an event-based neuromorphic vision sensor. We further demonstrate the advantages of the R-STDP approach in terms of the lateral localization accuracy and training time steps by comparing them with other three algorithms presented in this paper.

cs.NE↗

arXiv2020

Identity Recognition in Intelligent Cars with Behavioral Data and LSTM-ResNet Classifier

Identity recognition in a car cabin is a critical task nowadays and offers a great field of applications ranging from personalizing intelligent cars to suit drivers physical and behavioral needs to increasing safety and security. However, the performance and applicability of published approaches are still not suitable for use in series cars and need to be improved. In this paper, we investigate Human Identity Recognition in a car cabin with Time Series Classification (TSC) and deep neural networks. We use gas and brake pedal pressure as input to our models. This data is easily collectable during driving in everyday situations. Since our classifiers have very little memory requirements and do not require any input data preproccesing, we were able to train on one Intel i5-3210M processor only. Our classification approach is based on a combination of LSTM and ResNet. The network trained on a subset of NUDrive outperforms the ResNet and LSTM models trained solely by 35.9 % and 53.85 % accuracy respectively. We reach a final accuracy of 79.49 % on a 10-drivers subset of NUDrive and 96.90 % on a 5-drivers subset of UTDrive.

cs.CV↗

arXiv2020

What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction

Pedestrian motion prediction is a fundamental task for autonomous robots and vehicles to operate safely. In recent years many complex approaches based on neural networks have been proposed to address this problem. In this work we show that - surprisingly - a simple Constant Velocity Model can outperform even state-of-the-art neural models. This indicates that either neural networks are not able to make use of the additional information they are provided with, or that this information is not as relevant as commonly believed. Therefore, we analyze how neural networks process their input and how it impacts their predictions. Our analysis reveals pitfalls in training neural networks for pedestrian motion prediction and clarifies false assumptions about the problem itself. In particular, neural networks implicitly learn environmental priors that negatively impact their generalization capability, the motion history of pedestrians is irrelevant and interactions are too complex to predict. Our work shows how neural networks for pedestrian motion prediction can be thoroughly evaluated and our results indicate which research directions for neural motion prediction are promising in future.

cs.CV↗

arXiv2019

Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks

Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail. We show that the choice of starting points is indeed crucial, and that the performance of state-of-the-art attacks depends on it. First, we discuss desirable properties of starting points for attacking image classifiers, and how they can be chosen to increase query efficiency. Notably, we find that simply copying small patches from other images is a valid strategy. We then present an evaluation on ImageNet that clearly demonstrates the effectiveness of this method: Our initialization scheme reduces the number of queries required for a state-of-the-art Boundary Attack by 81%, significantly outperforming previous results reported for targeted black-box adversarial examples.

cs.CV↗

arXiv2019

Bridging the Gap between Open Source Software and Vehicle Hardware for Autonomous Driving

Although many research vehicle platforms for autonomous driving have been built in the past, hardware design, source code and lessons learned have not been made available for the next generation of demonstrators. This raises the efforts for the research community to contribute results based on real-world evaluations as engineering knowledge of building and maintaining a research vehicle is lost. In this paper, we deliver an analysis of our approach to transferring an open source driving stack to a research vehicle. We put the hardware and software setup in context to other demonstrators and explain the criteria that led to our chosen hardware and software design. Specifically, we discuss the mapping of the Apollo driving stack to the system layout of our research vehicle, fortuna, including communication with the actuators by a controller running on a real-time hardware platform and the integration of the sensor setup. With our collection of the lessons learned, we encourage a faster setup of such systems by other research groups in the future.

cs.RO↗

arXiv2019

From Specifications to Behavior: Maneuver Verification in a Semantic State Space

To realize a market entry of autonomous vehicles in the foreseeable future, the behavior planning system will need to abide by the same rules that humans follow. Product liability cannot be enforced without a proper solution to the approval trap. In this paper, we define a semantic abstraction of the continuous space and formalize traffic rules in linear temporal logic (LTL). Sequences in the semantic state space represent maneuvers a high-level planner could choose to execute. We check these maneuvers against the formalized traffic rules using runtime verification. By using the standard model checker NuSMV, we demonstrate the effectiveness of our approach and provide runtime properties for the maneuver verification. We show that high-level behavior can be verified in a semantic state space to fulfill a set of formalized rules, which could serve as a step towards safety of the intended functionality.

cs.RO↗

arXiv2019

Targetless Rotational Auto-Calibration of Radar and Camera for Intelligent Transportation Systems

Most intelligent transportation systems use a combination of radar sensors and cameras for robust vehicle perception. The calibration of these heterogeneous sensor types in an automatic fashion during system operation is challenging due to differing physical measurement principles and the high sparsity of traffic radars. We propose - to the best of our knowledge - the first data-driven method for automatic rotational radar-camera calibration without dedicated calibration targets. Our approach is based on a coarse and a fine convolutional neural network. We employ a boosting-inspired training algorithm, where we train the fine network on the residual error of the coarse network. Due to the unavailability of public datasets combining radar and camera measurements, we recorded our own real-world data. We demonstrate that our method is able to reach precise and robust sensor registration and show its generalization capabilities to different sensor alignments and perspectives.

cs.CV↗

arXiv2019

Leveraging Semantic Embeddings for Safety-Critical Applications

Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning. We observe their interpretability and discuss their potential utility in a safety-critical context. Concretely, we propose to use them to add introspection and error detection capabilities to neural network classifiers. First, we show how to create embeddings from symbolic domain knowledge. We discuss how to use them for interpreting mispredictions and propose a simple error detection scheme. We then introduce the concept of semantic distance: a real-valued score that measures confidence in the semantic space. We evaluate this score on a traffic sign classifier and find that it achieves near state-of-the-art performance, while being significantly faster to compute than other confidence scores. Our approach requires no changes to the original network and is thus applicable to any task for which domain knowledge is available.

stat.ML↗

arXiv2019

Graph Neural Networks for Modelling Traffic Participant Interaction

By interpreting a traffic scene as a graph of interacting vehicles, we gain a flexible abstract representation which allows us to apply Graph Neural Network (GNN) models for traffic prediction. These naturally take interaction between traffic participants into account while being computationally efficient and providing large model capacity. We evaluate two state-of-the art GNN architectures and introduce several adaptations for our specific scenario. We show that prediction error in scenarios with much interaction decreases by 30% compared to a model that does not take interactions into account. This suggests that interaction is important, and shows that we can model it using graphs. This makes GNNs a worthwhile addition to traffic prediction systems.

cs.LG↗