Francisco Munguia-Galeano

Francisco Munguia-Galeano, Ah-Hwee Tan, Ze Ji

Reinforcement learning (RL) has shown an outstanding capability for solving complex computational problems. However, most RL algorithms lack an explicit method that would allow learning from contextual information. Humans use context to identify patterns and relations among elements in the environment, along with how to avoid making wrong actions. On the other hand, what may seem like an obviously wrong decision from a human perspective could take hundreds of steps for an RL agent to learn to avoid. This paper proposes a framework for discrete environments called Iota explicit context representation (IECR). The framework involves representing each state using contextual key frames (CKFs), which can then be used to extract a function that represents the affordances of the state; in addition, two loss functions are introduced with respect to the affordances of the state. The novelty of the IECR framework lies in its capacity to extract contextual information from the environment and learn from the CKFs' representation. We validate the framework by developing four new algorithms that learn using context: Iota deep Q-network (IDQN), Iota double deep Q-network (IDDQN), Iota dueling deep Q-network (IDuDQN), and Iota dueling double deep Q-network (IDDDQN). Furthermore, we evaluate the framework and the new algorithms in five discrete environments. We show that all the algorithms, which use contextual information, converge in around 40,000 training steps of the neural networks, significantly outperforming their state-of-the-art equivalents.

Francisco Munguia-Galeano, Jihong Zhu, Juan David Hernández et al.

Bagging is an essential skill that humans perform in their daily activities. However, deformable objects, such as bags, are complex for robots to manipulate. This paper presents an efficient learning-based framework that enables robots to learn bagging. The novelty of this framework is its ability to perform bagging without relying on simulations. The learning process is accomplished through a reinforcement learning algorithm introduced in this work, designed to find the best grasping points of the bag based on a set of compact state representations. The framework utilizes a set of primitive actions and represents the task in five states. In our experiments, the framework reaches a 60 % and 80 % of success rate after around three hours of training in the real world when starting the bagging task from folded and unfolded, respectively. Finally, we test the trained model with two more bags of different sizes to evaluate its generalizability.

Francisco Munguia-Galeano, Zhengxue Zhou, Satheeshkumar Veeramani et al.

The integration of robotics and automation into self-driving laboratories (SDLs) can introduce additional safety complexities, in addition to those that already apply to conventional research laboratories. Personal protective equipment (PPE) is an essential requirement for ensuring the safety and well-being of workers in laboratories, self-driving or otherwise. Fires are another important risk factor in chemical laboratories. In SDLs, fires that occur close to mobile robots, which use flammable lithium batteries, could have increased severity. Here, we present Chemist Eye, a distributed safety monitoring system designed to enhance situational awareness in SDLs. The system integrates multiple stations equipped with RGB, depth, and infrared cameras, designed to monitor incidents in SDLs. Chemist Eye is also designed to spot workers who have suffered a potential accident or medical emergency, PPE compliance and fire hazards. To do this, Chemist Eye uses decision-making driven by a vision-language model (VLM). Chemist Eye is designed for seamless integration, enabling real-time communication with robots. Based on the VLM recommendations, the system attempts to drive mobile robots away from potential fire locations, exits, or individuals not wearing PPE, and issues audible warnings where necessary. It also integrates with third-party messaging platforms to provide instant notifications to lab personnel. We tested Chemist Eye with real-world data from an SDL equipped with three mobile robots and found that the spotting of possible safety hazards and decision-making performances reached 97 % and 95 %, respectively.