Waypoint-Based Reinforcement Learning for Robot Manipulation Tasks

Robot arms should be able to learn new tasks. One framework here is reinforcement learning, where the robot is given a reward function that encodes the task, and the robot autonomously learns actions to maximize its reward. Existing approaches to reinforcement learning often frame this problem as a Markov decision process, and learn a policy (or a hierarchy of policies) to complete the task. These policies reason over hundreds of fine-grained actions that the robot arm needs to take: e.g., moving slightly to the right or rotating the end-effector a few degrees. But the manipulation tasks that we want robots to perform can often be broken down into a small number of high-level motions: e.g., reaching an object or turning a handle. In this paper we therefore propose a waypoint-based approach for model-free reinforcement learning. Instead of learning a low-level policy, the robot now learns a trajectory of waypoints, and then interpolates between those waypoints using existing controllers. Our key novelty is framing this waypoint-based setting as a sequence of multi-armed bandits: each bandit problem corresponds to one waypoint along the robot's motion. We theoretically show that an ideal solution to this reformulation has lower regret bounds than standard frameworks. We also introduce an approximate posterior sampling solution that builds the robot's motion one waypoint at a time. Results across benchmark simulations and two real-world experiments suggest that this proposed approach learns new tasks more quickly than state-of-the-art baselines. See videos here: https://youtu.be/MMEd-lYfq4Y

Aligning Learning with Communication in Shared Autonomy

Assistive robot arms can help humans by partially automating their desired tasks. Consider an adult with motor impairments controlling an assistive robot arm to eat dinner. The robot can reduce the number of human inputs -- and how precise those inputs need to be -- by recognizing what the human wants (e.g., a fork) and assisting for that task (e.g., moving towards the fork). Prior research has largely focused on learning the human's task and providing meaningful assistance. But as the robot learns and assists, we also need to ensure that the human understands the robot's intent (e.g., does the human know the robot is reaching for a fork?). In this paper, we study the effects of communicating learned assistance from the robot back to the human operator. We do not focus on the specific interfaces used for communication. Instead, we develop experimental and theoretical models of a) how communication changes the way humans interact with assistive robot arms, and b) how robots can harness these changes to better align with the human's intent. We first conduct online and in-person user studies where participants operate robots that provide partial assistance, and we measure how the human's inputs change with and without communication. With communication, we find that humans are more likely to intervene when the robot incorrectly predicts their intent, and more likely to release control when the robot correctly understands their task. We then use these findings to modify an established robot learning algorithm so that the robot can correctly interpret the human's inputs when communication is present. Our results from a second in-person user study suggest that this combination of communication and learning outperforms assistive systems that isolate either learning or communication.

Accelerating Interface Adaptation with User-Friendly Priors

Robots often need to convey information to human users. For example, robots can leverage visual, auditory, and haptic interfaces to display their intent or express their internal state. In some scenarios there are socially agreed upon conventions for what these signals mean: e.g., a red light indicates an autonomous car is slowing down. But as robots develop new capabilities and seek to convey more complex data, the meaning behind their signals is not always mutually understood: one user might think a flashing light indicates the autonomous car is an aggressive driver, while another user might think the same signal means the autonomous car is defensive. In this paper we enable robots to adapt their interfaces to the current user so that the human's personalized interpretation is aligned with the robot's meaning. We start with an information theoretic end-to-end approach, which automatically tunes the interface policy to optimize the correlation between human and robot. But to ensure that this learning policy is intuitive -- and to accelerate how quickly the interface adapts to the human -- we recognize that humans have priors over how interfaces should function. For instance, humans expect interface signals to be proportional and convex. Our approach biases the robot's interface towards these priors, resulting in signals that are adapted to the current user while still following social expectations. Our simulations and user study results across $15$ participants suggest that these priors improve robot-to-human communication. See videos here: https://youtu.be/Re3OLg57hp8

Kiri-Spoon: A Soft Shape-Changing Utensil for Robot-Assisted Feeding

Assistive robot arms have the potential to help disabled or elderly adults eat everyday meals without relying on a caregiver. To provide meaningful assistance, these robots must reach for food items, pick them up, and then carry them to the human's mouth. Current work equips robot arms with standard utensils (e.g., forks and spoons). But -- although these utensils are intuitive for humans -- they are not easy for robots to control. If the robot arm does not carefully and precisely orchestrate its motion, food items may fall out of a spoon or slide off of the fork. Accordingly, in this paper we design, model, and test Kiri-Spoon, a novel utensil specifically intended for robot-assisted feeding. Kiri-Spoon combines the familiar shape of traditional utensils with the capabilities of soft grippers. By actuating a kirigami structure the robot can rapidly adjust the curvature of Kiri-Spoon: at one extreme the utensil wraps around food items to make them easier for the robot to pick up and carry, and at the other extreme the utensil returns to a typical spoon shape so that human users can easily take a bite of food. Our studies with able-bodied human operators suggest that robot arms equipped with Kiri-Spoon carry foods more robustly than when leveraging traditional utensils. See videos here: https://youtu.be/nddAniZLFPk

Safely and Autonomously Cutting Meat with a Collaborative Robot Arm

Labor shortages in the United States are impacting a number of industries including the meat processing sector. Collaborative technologies that work alongside humans while increasing production abilities may support the industry by enhancing automation and improving job quality. However, existing automation technologies used in the meat industry have limited collaboration potential, low flexibility, and high cost. The objective of this work was to explore the use of a robot arm to collaboratively work alongside a human and complete tasks performed in a meat processing facility. Toward this objective, we demonstrated proof-of-concept approaches to ensure human safety while exploring the capacity of the robot arm to perform example meat processing tasks. In support of human safety, we developed a knife instrumentation system to detect when the cutting implement comes into contact with meat within the collaborative space. To demonstrate the capability of the system to flexibly conduct a variety of basic meat processing tasks, we developed vision and control protocols to execute slicing, trimming, and cubing of pork loins. We also collected a subjective evaluation of the actions from experts within the U.S. meat processing industry. On average the experts rated the robot's performance as adequate. Moreover, the experts generally preferred the cuts performed in collaboration with a human worker to cuts completed autonomously, highlighting the benefits of robotic technologies that assist human workers rather than replace them. Video demonstrations of our proposed framework can be found here: https://youtu.be/56mdHjjYMVc

A Review of Communicating Robot Learning during Human-Robot Interaction

For robots to seamlessly interact with humans, we first need to make sure that humans and robots understand one another. Diverse algorithms have been developed to enable robots to learn from humans (i.e., transferring information from humans to robots). In parallel, visual, haptic, and auditory communication interfaces have been designed to convey the robot's internal state to the human (i.e., transferring information from robots to humans). Prior research often separates these two directions of information transfer, and focuses primarily on either learning algorithms or communication interfaces. By contrast, in this review we take an interdisciplinary approach to identify common themes and emerging trends that close the loop between learning and communication. Specifically, we survey state-of-the-art methods and outcomes for communicating a robot's learning back to the human teacher during human-robot interaction. This discussion connects human-in-the-loop learning methods and explainable robot learning with multi-modal feedback systems and measures of human-robot interaction. We find that -- when learning and communication are developed together -- the resulting closed-loop system can lead to improved human teaching, increased human trust, and human-robot co-adaptation. The paper includes a perspective on several of the interdisciplinary research themes and open questions that could advance how future robots communicate their learning to everyday operators. Finally, we implement a selection of the reviewed methods in a case study where participants kinesthetically teach a robot arm. This case study documents and tests an integrated approach for learning in ways that can be communicated, conveying this learning across multi-modal interfaces, and measuring the resulting changes in human and robot behavior. See videos of our case study here: https://youtu.be/EXfQctqFzWs

StROL: Stabilized and Robust Online Learning from Humans

Today's robots can learn the human's reward function online, during the current interaction. This real-time learning requires fast but approximate learning rules; when the human's behavior is noisy or suboptimal, today's approximations can result in unstable robot learning. Accordingly, in this paper we seek to enhance the robustness and convergence properties of gradient descent learning rules when inferring the human's reward parameters. We model the robot's learning algorithm as a dynamical system over the human preference parameters, where the human's true (but unknown) preferences are the equilibrium point. This enables us to perform Lyapunov stability analysis to derive the conditions under which the robot's learning dynamics converge. Our proposed algorithm (StROL) takes advantage of these stability conditions offline to modify the original learning dynamics: we introduce a corrective term that expands the basins of attraction around likely human rewards. In practice, our modified learning rule can correctly infer what the human is trying to convey, even when the human is noisy, biased, and suboptimal. Across simulations and a user study we find that StROL results in a more accurate estimate and less regret than state-of-the-art approaches for online reward learning. See videos here: https://youtu.be/uDGpkvJnY8g

Reward Learning with Intractable Normalizing Functions

Robots can learn to imitate humans by inferring what the human is optimizing for. One common framework for this is Bayesian reward learning, where the robot treats the human's demonstrations and corrections as observations of their underlying reward function. Unfortunately, this inference is doubly-intractable: the robot must reason over all the trajectories the person could have provided and all the rewards the person could have in mind. Prior work uses existing robotic tools to approximate this normalizer. In this paper, we group previous approaches into three fundamental classes and analyze the theoretical pros and cons of their approach. We then leverage recent research from the statistics community to introduce Double MH reward learning, a Monte Carlo method for asymptotically learning the human's reward in continuous spaces. We extend Double MH to conditionally independent settings (where each human correction is viewed as completely separate) and conditionally dependent environments (where the human's current correction may build on previous inputs). Across simulations and user studies, our proposed approach infers the human's reward parameters more accurately than the alternate approximations when learning from either demonstrations or corrections. See videos here: https://youtu.be/EkmT3o5K5ko

Should Collaborative Robots be Transparent?

Today's robots often assume that their behavior should be transparent. These transparent (e.g., legible, explainable) robots intentionally choose actions that convey their internal state to nearby humans. But while transparent behavior seems beneficial, is it actually optimal? In this paper we consider collaborative settings where the human and robot have the same objective, and the human is uncertain about the robot's type (i.e., the robot's internal state). We extend a recursive combination of Bayesian Nash equilibrium and the Bellman equation to solve for optimal robot policies. Interestingly, we discover that it is not always optimal for collaborative robots to be transparent; instead, human and robot teams can sometimes achieve higher rewards when the robot is opaque. Opaque robots select the same actions regardless of their internal state: because each type of opaque robot behaves in the same way, the human cannot infer the robot's type. Our analysis suggests that opaque behavior becomes optimal when either (a) human-robot interactions have a short time horizon or (b) users are slow to learn from the robot's actions. Across online and in-person user studies with 43 total participants, we find that users reach higher rewards when working with opaque partners, and subjectively rate opaque robots as about equal to transparent robots. See videos of our experiments here: https://youtu.be/u8q1Z7WHUuI

LIMIT: Learning Interfaces to Maximize Information Transfer

Robots can use auditory, visual, or haptic interfaces to convey information to human users. The way these interfaces select signals is typically pre-defined by the designer: for instance, a haptic wristband might vibrate when the robot is moving and squeeze when the robot stops. But different people interpret the same signals in different ways, so that what makes sense to one person might be confusing or unintuitive to another. In this paper we introduce a unified algorithmic formalism for learning co-adaptive interfaces from scratch. Our method does not need to know the human's task (i.e., what the human is using these signals for). Instead, our insight is that interpretable interfaces should select signals that maximize correlation between the human's actions and the information the interface is trying to convey. Applying this insight we develop LIMIT: Learning Interfaces to Maximize Information Transfer. LIMIT optimizes a tractable, real-time proxy of information gain in continuous spaces. The first time a person works with our system the signals may appear random; but over repeated interactions the interface learns a one-to-one mapping between displayed signals and human responses. Our resulting approach is both personalized to the current user and not tied to any specific interface modality. We compare LIMIT to state-of-the-art baselines across controlled simulations, an online survey, and an in-person user study with auditory, visual, and haptic interfaces. Overall, our results suggest that LIMIT learns interfaces that enable users to complete the task more quickly and efficiently, and users subjectively prefer LIMIT to the alternatives. See videos here: https://youtu.be/IvQ3TM1_2fA.