Explore the vast range of titles available.

In the digital age, innovative technologies such as social media, mobile computing, data analytics, cloud computing, internet of things (SMACIT), and more recently blockchain, artificial intelligence, and virtual reality significantly influence work processes, products, services, and business models. Digitalization has therefore increased the importance of information technology (IT), and it has transformed the demands placed on organizations’ IT functions. The business activity does not only become more efficient, but it is also no longer imaginable without IT. Since information technologies are now applied to realize innovations for businesses—something that will increase in the future—IT functions are required to cooperate proactively and early on with business departments to be able to develop and implement such innovations jointly. Besides ensuring regular IT operations, IT functions are increasingly required to identify technological innovations proactively and rapidly transfer them into marketable solutions, thereby directly contributing to the company’s central value proposition (Urbach et al. 2017).

Design-oriented research in general and action design research in particular aims to impact the real world in a way that has demonstrably positive outcomes for organizations or society. However, the current methodological guidance for action design research currently lacks a way to proactively incorporate the consideration of values into the resulting designs and interventions. Values are often a crucial aspect in the responsible design of technologies to achieve sustainably positive organizational or societal effects. The value sensitive design approach is seen as a promising way to achieve this. In this paper, we propose an extension of the action design research tasks with value sensitive design considerations and introduce the value-sensitive decision log method to trace how values underpinned and influenced design decisions. Both contributions were developed based on reflections and method enhancement in an action design research project aiming at developing a digital social innovation for supporting humans experiencing homelessness. Researchers and other participants in action design research projects can draw on our approach to better incorporate value-sensitive decisions in the action design research process

Coupling of control and perception is an especially difficult problem. This thesis investigates this problem in the context of aggressive off-road driving. By jointly developing a robust 1:5 scale platform and leveraging state of the art sampling based model predictive control, the problem of aggressive driving on a closed dirt track using only monocular camera images is addressed. It is shown that a convolutional neural network can directly learn a mapping from input images to top-down cost map. This cost map can be used by a model predictive control algorithm to drive aggressively and repeatably at the limits of grip. Further, the ability to learn an end-to-end trained attentional neural network gaze strategy is developed that allows both high performance and better generalization at our task of high speed driving. This gaze model allows us to utilize simulation data to generalize from our smaller oval track to a much more complex track setting. This gaze model is compared with that of human drivers performing the same task. Using these methods, repeatable, aggressive driving at the limits of handling using monocular camera images is shown on a physical robot.

We represent a vehicle dynamics model for autonomous driving near the limits of handling via a multi-layer neural network. Online adaptation is desirable in order to address unseen environments. However, the model needs to adapt to new environments without forgetting previously encountered ones. In this study, we apply Continual-MAML to overcome this difficulty. It enables the model to adapt to the previously encountered environments quickly and efficiently by starting updates from optimized initial parameters. We evaluate the impact of online model adaptation with respect to inference performance and impact on control performance of a model predictive path integral (MPPI) controller using the TRIKart platform. The neural network was pre-trained using driving data collected in our test environment, and experiments for online adaptation were executed on multiple different road conditions not contained in the training data. Empirical results show that the model using Continual-MAML outperforms the fixed model and the model using gradient descent in test set loss and online tracking performance of MPPI.

Game theoretic methods have become popular for planning and prediction in situations involving rich multi-agent interactions. However, these methods often assume the existence of a single local Nash equilibria and are hence unable to handle uncertainty in the intentions of different agents. While maximum entropy (MaxEnt) dynamic games try to address this issue, practical approaches solve for MaxEnt Nash equilibria using linear-quadratic approximations which are restricted to unimodal responses and unsuitable for scenarios with multiple local Nash equilibria. By reformulating the problem as a POMDP, we propose MPOGames, a method for efficiently solving MaxEnt dynamic games that captures the interactions between local Nash equilibria. We show the importance of uncertainty-aware game theoretic methods via a two-agent merge case study. Finally, we prove the real-time capabilities of our approach with hardware experiments on a 1/10th scale car platform.

Trials cyclists and mountain bike riders can hop, jump, balance, and drive on one or both wheels. This versatility allows them to achieve speed and energy-efficiency on smooth terrain and agility over rough terrain. Inspired by these athletes, we present the design and control of a robotic platform, Ultra Mobility Vehicle (UMV), which combines a bicycle and a reaction mass to move dynamically with minimal actuated degrees of freedom. We employ a simulation-driven design optimization process to synthesize a spatial linkage topology with a focus on vertical jump height and momentum-based balancing on a single wheel contact. Using a constrained Reinforcement Learning (RL) framework, we demonstrate zero-shot transfer of diverse athletic behaviors, including track-stands, jumps, wheelies, rear wheel hopping, and front flips. This 23.5 kg robot is capable of high speeds (8 m/s) and jumping on and over large obstacles (1 m tall, or 130% of the robot's nominal height).

In this paper we present a framework for combining deep learning-based road detection, particle filters, and Model Predictive Control (MPC) to drive aggressively using only a monocular camera, IMU, and wheel speed sensors. This framework uses deep convolutional neural networks combined with LSTMs to learn a local cost map representation of the track in front of the vehicle. A particle filter uses this dynamic observation model to localize in a schematic map, and MPC is used to drive aggressively using this particle filter based state estimate. We show extensive real world testing results, and demonstrate reliable operation of the vehicle at the friction limits on a complex dirt track. We reach speeds above 27 mph (12 m/s) on a dirt track with a 105 foot (32m) long straight using our 1:5 scale test vehicle. A video of these results can be found at https://www.youtube.com/watch?v=5ALIK-z-vUg

This article presents AutoRally, a 1\\(:\\)5 scale robotics testbed for autonomous vehicle research. AutoRally is designed for robustness, ease of use, and reproducibility, so that a team of two people with limited knowledge of mechanical engineering, electrical engineering, and computer science can construct and then operate the testbed to collect real world autonomous driving data in whatever domain they wish to study. Complete documentation to construct and operate the platform is available online along with tutorials, example controllers, and a driving dataset collected at the Georgia Tech Autonomous Racing Facility. Offline estimation algorithms are used to determine parameters for physics-based dynamics models using an adaptive limited memory joint state unscented Kalman filter. Online vehicle state estimation using a factor graph optimization scheme and a convolutional neural network for semantic segmentation of drivable surface are presented. All algorithms are tested with real world data from the fleet of six AutoRally robots at the Georgia Tech Autonomous Racing Facility tracks, and serve as a demonstration of the robot\\('\\)s capabilities.

We present a framework for vision-based model predictive control (MPC) for the task of aggressive, high-speed autonomous driving. Our approach uses deep convolutional neural networks to predict cost functions from input video which are directly suitable for online trajectory optimization with MPC. We demonstrate the method in a high speed autonomous driving scenario, where we use a single monocular camera and a deep convolutional neural network to predict a cost map of the track in front of the vehicle. Results are demonstrated on a 1:5 scale autonomous vehicle given the task of high speed, aggressive driving.