Abstract-- T eleoperation is a key enabler for future mobility, supporting Automated V ehicles in rare and complex scenarios beyond the capabilities of their automation. Despite ongoing research, no open source software currently combines Remote Driving, e.g., via steering wheel and pedals, Remote Assistance through high-level interaction with automated driving software modules, and integration with a real-world vehicle for practical testing. T o address this gap, we present a modular, open source teleoperation software stack that can interact with an automated driving software, e.g., Autoware, enabling Remote Assistance and Remote Driving. The software features standardized interfaces for seamless integration with various real-world and simulation platforms, while allowing for flexible design of the human-machine interface. The system is designed for modularity and ease of extension, serving as a foundation for collaborative development on individual software components as well as realistic testing and user studies. T o demonstrate the applicability of our software, we evaluated the latency and performance of different vehicle platforms in simulation and real-world. Teleoperation enables remote support of robots over mobile networks, allowing humans to handle tasks that cannot be fully automated. In the field of intelligent vehicles, tele-operation has gained traction, with companies like Fernride and V ay deploying remote driving solutions for logistics and car sharing, gathering significant funding [1, 2]. Tele-operation also supports Automated V ehicles (A Vs) during disengagements, as seen with Waymo and Zoox, which rely on Remote Operators (ROs) when A Vs cannot resolve a scenario [3, 4].

Conventional robot programming methods are complex and time-consuming for users. In recent years, alternative approaches such as mixed reality have been explored to address these challenges and optimize robot programming. While the findings of the mixed reality robot programming methods are convincing, most existing methods rely on gesture interaction for robot programming. Since controller-based interactions have proven to be more reliable, this paper examines three controller-based programming methods within a mixed reality scenario: 1) Classical Jogging, where the user positions the robot's end effector using the controller's thumbsticks, 2) Direct Control, where the controller's position and orientation directly corresponds to the end effector's, and 3) Gripper Control, where the controller is enhanced with a 3D-printed gripper attachment to grasp and release objects. A within-subjects study (n = 30) was conducted to compare these methods. The findings indicate that the Gripper Control condition outperforms the others in terms of task completion time, user experience, mental demand, and task performance, while also being the preferred method. Therefore, it demonstrates promising potential as an effective and efficient approach for future robot programming. Video available at https://youtu.be/83kWr8zUFIQ.

Teleoperation is a popular solution to remotely support highly automated vehicles through a human remote operator whenever a disengagement of the automated driving system is present. The remote operator wirelessly connects to the vehicle and solves the disengagement through support or substitution of automated driving functions and therefore enables the vehicle to resume automation. There are different approaches to support automated driving functions on various levels, commonly known as teleoperation concepts. A variety of teleoperation concepts is described in the literature, yet there has been no comprehensive and structured comparison of these concepts, and it is not clear what subset of teleoperation concepts is suitable to enable safe and efficient remote support of highly automated vehicles in a broad spectrum of disengagements. The following work establishes a basis for comparing teleoperation concepts through a literature overview on automated vehicle disengagements and on already conducted studies on the comparison of teleoperation concepts and metrics used to evaluate teleoperation performance. An evaluation of the teleoperation concepts is carried out in an expert workshop, comparing different teleoperation concepts using a selection of automated vehicle disengagement scenarios and metrics. Based on the workshop results, a set of teleoperation concepts is derived that can be used to address a wide variety of automated vehicle disengagements in a safe and efficient way.

Text-guided diffusion models such as DALLE-2, Imagen, eDiff-I, and Stable Diffusion are able to generate an effectively endless variety of images given only a short text prompt describing the desired image content. In many cases the images are of very high quality. However, these models often struggle to compose scenes containing several key objects such as characters in specified positional relationships. The missing capability to ``direct'' the placement of characters and objects both within and across images is crucial in storytelling, as recognized in the literature on film and animation theory. In this work, we take a particularly straightforward approach to providing the needed direction. Drawing on the observation that the cross-attention maps for prompt words reflect the spatial layout of objects denoted by those words, we introduce an optimization objective that produces ``activation'' at desired positions in these cross-attention maps. The resulting approach is a step toward generalizing the applicability of text-guided diffusion models beyond single images to collections of related images, as in storybooks. Directed Diffusion provides easy high-level positional control over multiple objects, while making use of an existing pre-trained model and maintaining a coherent blend between the positioned objects and the background. Moreover, it requires only a few lines to implement.

The quantum instruction set (QIS) is defined as the quantum gates that are physically realizable by controlling the qubits in quantum hardware. Compiling quantum circuits into the product of the gates in a properly defined QIS is a fundamental step in quantum computing. We here propose the quantum variational instruction set (QuVIS) formed by flexibly designed multi-qubit gates for higher speed and accuracy of quantum computing. The controlling of qubits for realizing the gates in a QuVIS is variationally achieved using the fine-grained time optimization algorithm. Significant reductions in both the error accumulation and time cost are demonstrated in realizing the swaps of multiple qubits and quantum Fourier transformations, compared with the compiling by a standard QIS such as the quantum microinstruction set (QuMIS, formed by several one- and two-qubit gates including one-qubit rotations and controlled-NOT gates). With the same requirement on quantum hardware, the time cost for QuVIS is reduced to less than one half of that for QuMIS. Simultaneously, the error is suppressed algebraically as the depth of the compiled circuit is reduced. As a general compiling approach with high flexibility and efficiency, QuVIS can be defined for different quantum circuits and be adapted to the quantum hardware with different interactions.

Intrinsic rewards are introduced to simulate how human intelligence works; they are usually evaluated by intrinsically-motivated play, i.e., playing games without extrinsic rewards but evaluated with extrinsic rewards. However, none of the existing intrinsic reward approaches can achieve human-level performance under this very challenging setting of intrinsically-motivated play. In this work, we propose a novel megalomania-driven intrinsic reward (called \emph{mega-reward}), which, to our knowledge, is the first approach that achieves human-level performance in intrinsically-motivated play. Intuitively, mega-reward comes from the observation that infants' intelligence develops when they try to gain more control on entities in an environment; therefore, mega-reward aims to maximize the control capabilities of agents on given entities in a given environment. To formalize mega-reward, a relational transition model is proposed to bridge the gaps between direct and latent control. Experimental studies show that mega-reward can (i) greatly outperform all state-of-the-art intrinsic reward approaches, (ii) generally achieves the same level of performance as Ex-PPO and professional human-level scores; and (iii) has also superior performance when it is incorporated with extrinsic reward.

The ability of a footballer to outwit the goalkeeper depends in part on his ability to deliver the ball at an unpredictable time and location. Researchers have studied how we make sure such decisions are unpredictable, and found that the brain processes predictable and unpredictable components in different regions of the brain. This process ensures that we learn from experience, while still remaining spontaneous to get the competitive edge. Researchers set out to understand how the brain optimises the timing of actions to circumstance while retaining unpredictability. Readings were taken either in a region of the prefrontal cortex called MPFC, which is involved in decision-making learning, or in a region of the motor cortex, M2, thought to be involved in the direct control of movements.

When some of the world's most advanced rescue robots are foiled by nothing more complex than a doorknob, you get a good sense of the challenge of making our homes and workplaces more automated. At the DARPA Robotics Challenge, a contest held over the weekend in California, two dozen extremely sophisticated robots did their best to perform a series of tasks on an outdoor course, including turning a valve, climbing some steps, and opening a door (see "A Transformer Wins DARPA's $2 Million Robotics Challenge"). Although a couple of robots managed to complete the course, others grasped thin air, walked into walls, or simply toppled over as if overcome with the sheer impossibility of it all. At the same time, efforts by human controllers to help the robots through their tasks may offer clues as to how human-machine collaboration could be deployed in various other settings. "I think this is an opportunity for everybody to see how hard robotics really is," says Mark Raibert, founder of Boston Dynamics, now owned by Google, which produced an extremely sophisticated humanoid robot called Atlas (see "10 Breakthrough Technologies 2014: Agile Robots").