Recent advancements in Large Language Models (LLMs) and Visual Language Models (VLMs) have significantly impacted robotics, enabling high-level semantic motion planning applications. Reinforcement Learning (RL), a complementary paradigm, enables agents to autonomously optimize complex behaviors through interaction and reward signals. However, designing effective reward functions for RL remains challenging, especially in real-world tasks where sparse rewards are insufficient and dense rewards require elaborate design. In this work, we propose Autonomous Reinforcement learning for Complex HumanInformed Environments (ARCHIE), an unsupervised pipeline leveraging GPT-4, a pre-trained LLM, to generate reward functions directly from natural language task descriptions. The rewards are used to train RL agents in simulated environments, where we formalize the reward generation process to enhance feasibility. Additionally, GPT-4 automates the coding of task success criteria, creating a fully automated, one-shot procedure for translating human-readable text into deployable robot skills. Our approach is validated through extensive simulated experiments on single-arm and bi-manual manipulation tasks using an ABB YuMi collaborative robot, highlighting its practicality and effectiveness. Tasks are demonstrated on the real robot setup.

Behavior Trees (BTs) were first conceived in the computer games industry as a tool to model agent behavior, but they received interest also in the robotics community as an alternative policy design to Finite State Machines (FSMs). The advantages of BTs over FSMs had been highlighted in many works, but there is no thorough practical comparison of the two designs. Such a comparison is particularly relevant in the robotic industry, where FSMs have been the state-of-the-art policy representation for robot control for many years. In this work we shed light on this matter by comparing how BTs and FSMs behave when controlling a robot in a mobile manipulation task. The comparison is made in terms of reactivity, modularity, readability, and design. We propose metrics for each of these properties, being aware that while some are tangible and objective, others are more subjective and implementation dependent. The practical comparison is performed in a simulation environment with validation on a real robot. We find that although the robot's behavior during task solving is independent on the policy representation, maintaining a BT rather than an FSM becomes easier as the task increases in complexity.

In modern industrial collaborative robotic applications, it is desirable to create robot programs automatically, intuitively, and time-efficiently. Moreover, robots need to be controlled by reactive policies to face the unpredictability of the environment they operate in. In this paper we propose a framework that combines a method that learns Behavior Trees (BTs) from demonstration with a method that evolves them with Genetic Programming (GP) for collaborative robotic applications. The main contribution of this paper is to show that by combining the two learning methods we obtain a method that allows non-expert users to semi-automatically, time-efficiently, and interactively generate BTs. We validate the framework with a series of manipulation experiments. The BT is fully learnt in simulation and then transferred to a real collaborative robot.

Modern industrial applications require robots to be able to operate in unpredictable environments, and programs to be created with a minimal effort, as there may be frequent changes to the task. In this paper, we show that genetic programming can be effectively used to learn the structure of a behavior tree (BT) to solve a robotic task in an unpredictable environment. Moreover, we propose to use a simple simulator for the learning and demonstrate that the learned BTs can solve the same task in a realistic simulator, reaching convergence without the need for task specific heuristics. The learned solution is tolerant to faults, making our method appealing for real robotic applications.