Cooking robots can enhance the home experience by reducing the burden of daily chores. However, these robots must perform their tasks dexterously and safely in shared human environments, especially when handling dangerous tools such as kitchen knives. This study focuses on enabling a robot to autonomously and safely learn food-cutting tasks. More specifically, our goal is to enable a collaborative robot or industrial robot arm to perform food-slicing tasks by adapting to varying material properties using compliance control. Our approach involves using Reinforcement Learning (RL) to train a robot to compliantly manipulate a knife, by reducing the contact forces exerted by the food items and by the cutting board. However, training the robot in the real world can be inefficient, and dangerous, and result in a lot of food waste. Therefore, we proposed SliceIt!, a framework for safely and efficiently learning robot food-slicing tasks in simulation. Following a real2sim2real approach, our framework consists of collecting a few real food slicing data, calibrating our dual simulation environment (a high-fidelity cutting simulator and a robotic simulator), learning compliant control policies on the calibrated simulation environment, and finally, deploying the policies on the real robot.
This study tackles the representative yet challenging contact-rich peg-in-hole task of robotic assembly, using a soft wrist that can operate more safely and tolerate lower-frequency control signals than a rigid one. Previous studies often use a fully observable formulation, requiring external setups or estimators for the peg-to-hole pose. In contrast, we use a partially observable formulation and deep reinforcement learning from demonstrations to learn a memory-based agent that acts purely on haptic and proprioceptive signals. Moreover, previous works do not incorporate potential domain symmetry and thus must search for solutions in a bigger space. Instead, we propose to leverage the symmetry for sample efficiency by augmenting the training data and constructing auxiliary losses to force the agent to adhere to the symmetry. Results in simulation with five different symmetric peg shapes show that our proposed agent can be comparable to or even outperform a state-based agent. In particular, the sample efficiency also allows us to learn directly on the real robot within 3 hours.
Large language models (LLMs) are accelerating the development of language-guided robot planners. Meanwhile, symbolic planners offer the advantage of interpretability. This paper proposes a new task that bridges these two trends, namely, multimodal planning problem specification. The aim is to generate a problem description (PD), a machine-readable file used by the planners to find a plan. By generating PDs from language instruction and scene observation, we can drive symbolic planners in a language-guided framework. We propose a Vision-Language Interpreter (ViLaIn), a new framework that generates PDs using state-of-the-art LLM and vision-language models. ViLaIn can refine generated PDs via error message feedback from the symbolic planner. Our aim is to answer the question: How accurately can ViLaIn and the symbolic planner generate valid robot plans? To evaluate ViLaIn, we introduce a novel dataset called the problem description generation (ProDG) dataset. The framework is evaluated with four new evaluation metrics. Experimental results show that ViLaIn can generate syntactically correct problems with more than 99% accuracy and valid plans with more than 58% accuracy.
The Reinforcement Learning (RL) paradigm has been an essential tool for automating robotic tasks. Despite the advances in RL, it is still not widely adopted in the industry due to the need for an expensive large amount of robot interaction with its environment. Curriculum Learning (CL) has been proposed to expedite learning. However, most research works have been only evaluated in simulated environments, from video games to robotic toy tasks. This paper presents a study for accelerating robot learning of contact-rich manipulation tasks based on Curriculum Learning combined with Domain Randomization (DR). We tackle complex industrial assembly tasks with position-controlled robots, such as insertion tasks. We compare different curricula designs and sampling approaches for DR. Based on this study, we propose a method that significantly outperforms previous work, which uses DR only (No CL is used), with less than a fifth of the training time (samples). Results also show that even when training only in simulation with toy tasks, our method can learn policies that can be transferred to the real-world robot. The learned policies achieved success rates of up to 86\% on real-world complex industrial insertion tasks (with tolerances of $\pm 0.01~mm$) not seen during the training.
Robotic assembly tasks involve complex and low-clearance insertion trajectories with varying contact forces at different stages. While the nominal motion trajectory can be easily obtained from human demonstrations through kinesthetic teaching, teleoperation, simulation, among other methods, the force profile is harder to obtain especially when a real robot is unavailable. It is difficult to obtain a realistic force profile in simulation even with physics engines. Such simulated force profiles tend to be unsuitable for the actual robotic assembly due to the reality gap and uncertainty in the assembly process. To address this problem, we present a combined learning-based framework to imitate human assembly skills through hybrid trajectory learning and force learning. The main contribution of this work is the development of a framework that combines hierarchical imitation learning, to learn the nominal motion trajectory, with a reinforcement learning-based force control scheme to learn an optimal force control policy, that can satisfy the nominal trajectory while adapting to the force requirement of the assembly task. To further improve the imitation learning part, we develop a hierarchical architecture, following the idea of goal-conditioned imitation learning, to generate the trajectory learning policy on the \textit{skill} level offline. Through experimental validations, we corroborate that the proposed learning-based framework is robust to uncertainty in the assembly task, can generate high-quality trajectories, and can find suitable force control policies, which adapt to the task's force requirements more efficiently.