--The Large Language Models (LLM) are increasingly being deployed in robotics to generate robot control programs for specific user tasks, enabling embodied intelligence. Existing methods primarily focus on LLM training and prompt design that utilize LLMs to generate executable programs directly from user tasks in natural language. However, due to the inconsistency of the LLMs and the high complexity of the tasks, such best-effort approaches often lead to tremendous programming errors in the generated code, which significantly undermines the effectiveness especially when the light-weight LLMs are applied. This paper introduces a natural-robotic language translation framework that (i) provides correctness verification for generated control programs and (ii) enhances the performance of LLMs in program generation via feedback-based fine-tuning for the programs. T o achieve this, a Robot Skill Language (RSL) is proposed to abstract away from the intricate details of the control programs, bridging the natural language tasks with the underlying robot skills. Then, the RSL compiler and debugger are constructed to verify RSL programs generated by the LLM and provide error feedback to the LLM for refining the outputs until being verified by the compiler . This provides correctness guarantees for the LLM-generated programs before being offloaded to the robots for execution, significantly enhancing the effectiveness of LLMpowered robotic applications. Experiments demonstrate NRTrans outperforms the existing method under a range of LLMs and tasks, and achieves a high success rate for light-weight LLMs. To bridge this gap, LLMs ( e.g., OpenAI's GPT [4], Meta's Llama [5], and Google's Gemma [6]) are deployed in robotics, leveraging their semantic comprehension and contextual reasoning to generate robotic control programs that fulfill the given tasks. Most of the existing LLM-powered control program generation methods for robotics can be broadly categorized into the following three fundamental paradigms [7]-[9], as shown in Figure 1.

The combination of Large Language Models (LLMs), systematic evaluation, and evolutionary algorithms has enabled breakthroughs in combinatorial optimization and scientific discovery. We propose to extend this powerful combination to the control of dynamical systems, generating interpretable control policies capable of complex behaviors. With our novel method, we represent control policies as programs in standard languages like Python. We evaluate candidate controllers in simulation and evolve them using a pre-trained LLM. Unlike conventional learning-based control techniques, which rely on black box neural networks to encode control policies, our approach enhances transparency and interpretability. We still take advantage of the power of large AI models, but leverage it at the policy design phase, ensuring that all system components remain interpretable and easily verifiable at runtime. Additionally, the use of standard programming languages makes it straightforward for humans to finetune or adapt the controllers based on their expertise and intuition. We illustrate our method through its application to the synthesis of an interpretable control policy for the pendulum swing-up and the ball in cup tasks. We make the code available at https://github.com/muellerlab/synthesizing_interpretable_control_policies.git

Battery-less embedded devices powered by energy harvesting are increasingly being used in wireless sensing applications. However, their limited and often uncertain energy availability challenges designing application programs. To examine if BDI-based agent programming can address this challenge, we used it for a real-life application involving an environmental sensor that works on energy harvested from ambient light. This yielded the first ever implementation of a BDI agent on a low-power battery-less and energy-harvesting embedded system. Furthermore, it uncovered conceptual integration challenges between embedded systems and BDI-based agent programming that, if overcome, will simplify the deployment of more autonomous systems on low-power devices with non-deterministic energy availability. Specifically, we (1) mapped essential device states to default \textit{internal} beliefs, (2) recognized and addressed the need for beliefs in general to be \textit{short-} or \textit{long-term}, and (3) propose dynamic annotation of intentions with their run-time energy impact. We show that incorporating these extensions not only simplified the programming but also improved code readability and understanding of its behavior.

This past November, soon after OpenAI released ChatGPT, a software developer named Thomas Ptacek asked it to provide instructions for removing a peanut-butter sandwich from a VCR, written in the style of the King James Bible. ChatGPT rose to the occasion, generating six pitch-perfect paragraphs: "And he cried out to the Lord, saying, 'Oh Lord, how can I remove this sandwich from my VCR, for it is stuck fast and will not budge?' " Ptacek posted a screenshot of the exchange on Twitter. "I simply cannot be cynical about a technology that can accomplish this," he concluded. The nearly eighty thousand Twitter users who liked his interaction seemed to agree. A few days later, OpenAI announced that more than a million people had signed up to experiment with ChatGPT.

Educational robots allow experimenting with a variety of principles from mechanics, electronics, and informatics. Here we propose ClipBot, a low-cost, do-it-yourself, robot whose skeleton is made of two paper clips. An Arduino nano microcontroller actuates two servo motors that move the paper clips. However, such mechanical configuration confers physical impairments to movement. This creates the need for and allows experimenting with artificial intelligence methods to overcome hardware limitations. We report our experience in the usage of this robot during the study week 'fascinating informatics', organized by the Swiss Foundation Schweizer Jugend Forscht (www.sjf.ch). Students at the high school level were asked to implement a genetic algorithm to optimize the movements of the robot until it learned to walk. Such a methodology allowed the robot to learn the motor actuation scheme yielding straight movement in the forward direction using less than 20 iterations.

Crown-of-Thorn Starfish (COTS) outbreaks are a major cause of coral loss on the Great Barrier Reef (GBR) and substantial surveillance and control programs are underway in an attempt to manage COTS populations to ecologically sustainable levels. We release a large-scale, annotated underwater image dataset from a COTS outbreak area on the GBR, to encourage research on Machine Learning and AI-driven technologies to improve the detection, monitoring, and management of COTS populations at reef scale. The dataset is released and hosted in a Kaggle competition that challenges the international Machine Learning community with the task of COTS detection from these underwater images.

Autonomous agents can learn by imitating teacher demonstrations of the intended behavior. Hierarchical control policies are ubiquitously useful for such learning, having the potential to break down structured tasks into simpler sub-tasks, thereby improving data efficiency and generalization. In this paper, we propose a variational inference method for imitation learning of a control policy represented by parametrized hierarchical procedures (PHP), a program-like structure in which procedures can invoke sub-procedures to perform sub-tasks. Our method discovers the hierarchical structure in a dataset of observation-action traces of teacher demonstrations, by learning an approximate posterior distribution over the latent sequence of procedure calls and terminations. Samples from this learned distribution then guide the training of the hierarchical control policy. We identify and demonstrate a novel benefit of variational inference in the context of hierarchical imitation learning: in decomposing the policy into simpler procedures, inference can leverage acausal information that is unused by other methods. Training PHP with variational inference outperforms LSTM baselines in terms of data efficiency and generalization, requiring less than half as much data to achieve a 24% error rate in executing the bubble sort algorithm, and to achieve no error in executing Karel programs.

The field of adaptive robotics involves simulations and real-world implementations of robots that adapt to their environments. In this article, I introduce adaptive environmentics--the flip side of adaptive robotics--in which the environment adapts to the robot. The reasonable man adapts himself to the world; the unreasonable man persists to adapt the world to himself. Therefore, all progress depends on the unreasonable. The apparent complexity of its behavior over time is largely a reflection of the complexity of the environment in which it finds itself. Using both simulated and real robots, and applying techniques such as reinforcement learning, artificial neural networks, genetic algorithms, and fuzzy logic, researchers have obtained robots that display an amazing slew of behaviors and perform a multitude of tasks, including walking, pushing boxes, navigating, negotiating an obstacle course, playing ball, and foraging (Arkin 1998a). To cite one typical example of an ever-growing many, Yung and Ye (1999) recently wrote: We have presented a fuzzy navigator that performs well in complex and unknown environments, using a rule base that is learned from a simple corridor-like environment. The principle of the navigator is built on the fusion of the obstacle avoidance and goal seeking behaviors aided by an environment evaluator to tune the universe of discourse of the input sensor readings and enhance its adaptability. For this reason, the navigator has been able to learn extremely quickly in a simple environment, and then operate in an unknown environment, where exploration is not required at all. This quote typifies the underlying theme of adaptive robotics: Have a robot adapt to a given environment. Given signifies neither that the environment is known nor that it is static; it means that the robot must adapt to the quirks and idiosyncrasies imposed by the environment--which, for its part, does nothing at all to accommodate the puffing robot. This fundamental principle of adaptive robotics--the environment's unyielding nature--is repealed in this article. Dubbed adaptive environmentics, the basic idea is to create scenarios that are mirror images of those found in adaptive robotics: The environment adapts to a given robot. I hasten to say that in some cases, it is not possible to alter the environment, and in other cases, having the robot adapt is simply the underlying objective. Adaptive robotics has produced many interesting results based on these principles.

A wide range of sensor-rich, networked embedded systems are being created that must operate robustly for years in the face of novel failures by managing complex autonomic processes. These systems are being composed, for example, into vast networks of space, air, ground, and underwater vehicles. Our objective is to revolutionize the way in which we control these new artifacts by creating reactive model-based programming languages that enable everyday systems to reason intelligently and enable machines to explore other worlds. A model-based program is state and fault aware; it elevates the programming task to specifying intended state evolutions of a system. The program's executive automatically coordinates system interactions to achieve these states, entertaining known and potential failures, using models of its constituents and environment.

Would you like to make a robot to grasp something, but you think that is impossible to you just because you can't buy a robot arm? I'm here to tell that you can definitely achieve this without buying a real robot. The Smart Grasping Sandbox built by Shadow Robotics is now available for everybody on the ROS Development Studio – a system that allows you to create and test your robot programs through simulations using only a web browser. The Smart Grasping Sandbox is a public simulation for the Shadow's Smart Grasping System with theUR10 robot from Universal Robots. It allows you to make a robot to grasp something without having to learn everything related to Machine Learning, and being available on the ROS Development Studio, it allows you to test it without the hassle of installing all the requirements.