We develop AI agents based on instruction-finetuned large language models (LLMs) to assist in the engineering and operation of the Cherenkov Telescope Array Observatory (CT AO) Control and Data Acquisition Software (ACADA). These agents align with project-specific documentation and codebases, understand contextual information, interact with external APIs, and communicate with users in natural language.

Sensors play a fundamental role in achieving the complex behaviors typically found in biological organisms. However, their potential role in the design of artificial agents is often overlooked. This often results in the design of robots that are poorly adapted to the environment, compared to their biological counterparts. This paper proposes a formalization of a novel architectural component, called a metasensor, which enables a process of sensor evolution reminiscent of what occurs in living organisms. Even in online scenarios, the metasensor layer searches for the optimal interpretation of its input signals and then feeds them to the robotic agent to accomplish the assigned task.

Automatic design is a promising approach to realizing robot swarms. Given a mission to be performed by the swarm, an automatic method produces the required control software for the individual robots. Automatic design has concentrated on missions that a swarm can execute independently, interacting only with a static environment and without the involvement of other active entities. In this paper, we investigate the design of robot swarms that perform their mission by interacting with other robots that populate their environment. We frame our research within robot shepherding: the problem of using a small group of robots, the shepherds, to coordinate a relatively larger group, the sheep. In our study, the group of shepherds is the swarm that is automatically designed, and the sheep are pre-programmed robots that populate its environment. We use automatic modular design and neuroevolution to produce the control software for the swarm of shepherds to coordinate the sheep. We show that automatic design can leverage mission-specific interaction strategies to enable an effective coordination between the two groups.

The solution of the path structured multimarginal Schr\"{o}dinger bridge problem (MSBP) is the most-likely measure-valued trajectory consistent with a sequence of observed probability measures or distributional snapshots. We leverage recent algorithmic advances in solving such structured MSBPs for learning stochastic hardware resource usage by control software. The solution enables predicting the time-varying distribution of hardware resource availability at a desired time with guaranteed linear convergence. We demonstrate the efficacy of our probabilistic learning approach in a model predictive control software execution case study. The method exhibits rapid convergence to an accurate prediction of hardware resource utilization of the controller. The method can be broadly applied to any software to predict cyber-physical context-dependent performance at arbitrary time.

Automatic off-line design is an attractive approach to implementing robot swarms. In this approach, a designer specifies a mission for the swarm, and an optimization process generates suitable control software for the individual robots through computer-based simulations. Most relevant literature has focused on effectively transferring control software from simulation to physical robots. For the first time, we investigate (i) whether control software generated via automatic design is transferable across robot platforms and (ii) whether the design methods that generate such control software are themselves transferable. We experiment with two ground mobile platforms with equivalent capabilities. Our measure of transferability is based on the performance drop observed when control software and/or design methods are ported from one platform to another. Results indicate that while the control software generated via automatic design is transferable in some cases, better performance can be achieved when a transferable method is directly applied to the new platform.

Automatic design is a promising approach to generating control software for robot swarms. So far, automatic design has relied on mission-specific objective functions to specify the desired collective behavior. In this paper, we explore the possibility to specify the desired collective behavior via demonstrations. We develop Demo-Cho, an automatic design method that combines inverse reinforcement learning with automatic modular design of control software for robot swarms. We show that, only on the basis of demonstrations and without the need to be provided with an explicit objective function, Demo-Cho successfully generated control software to perform four missions. We present results obtained in simulation and with physical robots.

Life sciences manufacturing is on the cusp of a seismic shift. Companies are beginning to understand that their focus needs to move from documents to data because data leads to insights and competitive advantages. The benefits of and initiatives that lead to a data-centric mindset dovetail nicely into those related to a quality mindset. Fortunately, these are synergistic goals. Making data-based decisions improves quality.

As the world waits for construction of the largest fusion reactor yet, called ITER, smaller reactors with similar designs are still running. These reactors, called tokamaks, help us test both hardware and software. The hardware testing helps us refine things like the materials used for container walls or the shape and location of control magnets. But arguably, the software is the most important. To enable fusion, the control software of a tokamak has to monitor the state of the plasma it contains and respond to any changes by making real-time adjustments to the system's magnets.

We investigate the possibilities, challenges, and limitations that arise from the use of behavior trees in the context of the automatic modular design of collective behaviors in swarm robotics. To do so, we introduce Maple, an automatic design method that combines predefined modules—low-level behaviors and conditions—into a behavior tree that encodes the individual behavior of each robot of the swarm. We present three empirical studies based on two missions: aggregation and Foraging. To explore the strengths and weaknesses of adopting behavior trees as a control architecture, we compare Maple with Chocolate, a previously proposed automatic design method that uses probabilistic finite state machines instead. In the first study, we assess Maple’s ability to produce control software that crosses the reality gap satisfactorily. In the second study, we investigate Maple’s performance as a function of the design budget, that is, the maximum number of simulation runs that the design process is allowed to perform. In the third study, we explore a number of possible variants of Maple that differ in the constraints imposed on the structure of the behavior trees generated. The results of the three studies indicate that, in the context of swarm robotics, behavior trees might be appealing but in many settings do not produce better solutions than finite state machines.

Let's face it, robots are cool. They're also going to run the world some day, and hopefully, at that time they will take pity on their poor soft fleshy creators (a.k.a. I'm joking of course, but only sort of. In my ambition to have some small influence over the matter, I took a course in autonomous robot control theory last year, which culminated in my building a Python-based robotic simulator that allowed me to practice control theory on a simple, mobile, programmable robot. In this article, I'm going to show how to use a Python robot framework to develop control software, describe the control scheme I developed for my simulated robot, illustrate how it interacts with its environment and achieves its goals, and discuss some of the fundamental challenges of robotics programming that I encountered along the way. The snippets of code shown here are just a part of the entire simulator, which relies on classes and interfaces, so in order to read the code directly, you may need some experience in Python and object oriented programming. Finally, optional topics that will help you to better follow this tutorial are knowing what a state machine is and how range sensors and encoders work. The fundamental challenge of all robotics is this: It is impossible to ever know the true state of the environment. Robot control software can only guess the state of the real world based on measurements returned by its sensors. It can only attempt to change the state of the real world through the generation of control signals.