Reward functions are a common way to specify the objective of a robot. As designing reward functions can be extremely challenging, a more promising approach is to directly learn reward functions from human teachers. Importantly, data from human teachers can be collected either passively or actively in a variety of forms: passive data sources include demonstrations (e.g., kinesthetic guidance), whereas preferences (e.g., comparative rankings) are actively elicited. Prior research has independently applied reward learning to these different data sources. However, there exist many domains where multiple sources are complementary and expressive. Motivated by this general problem, we present a framework to integrate multiple sources of information, which are either passively or actively collected from human users. In particular, we present an algorithm that first utilizes user demonstrations to initialize a belief about the reward function, and then actively probes the user with preference queries to zero-in on their true reward. This algorithm not only enables us combine multiple data sources, but it also informs the robot when it should leverage each type of information. Further, our approach accounts for the human’s ability to provide data: yielding user-friendly preference queries which are also theoretically optimal. Our extensive simulated experiments and user studies on a Fetch mobile manipulator demonstrate the superiority and the usability of our integrated framework.
more »
« less
This content will become publicly available on November 7, 2024
Active preference-based Gaussian process regression for reward learning and optimization
Designing reward functions is a difficult task in AI and robotics. The complex task of directly specifying all the desirable behaviors a robot needs to optimize often proves challenging for humans. A popular solution is to learn reward functions using expert demonstrations. This approach, however, is fraught with many challenges. Some methods require heavily structured models, for example, reward functions that are linear in some predefined set of features, while others adopt less structured reward functions that may necessitate tremendous amounts of data. Moreover, it is difficult for humans to provide demonstrations on robots with high degrees of freedom, or even quantifying reward values for given trajectories. To address these challenges, we present a preference-based learning approach, where human feedback is in the form of comparisons between trajectories. We do not assume highly constrained structures on the reward function. Instead, we employ a Gaussian process to model the reward function and propose a mathematical formulation to actively fit the model using only human preferences. Our approach enables us to tackle both inflexibility and data-inefficiency problems within a preference-based learning framework. We further analyze our algorithm in comparison to several baselines on reward optimization, where the goal is to find the optimal robot trajectory in a data-efficient way instead of learning the reward function for every possible trajectory. Our results in three different simulation experiments and a user study show our approach can efficiently learn expressive reward functions for robotic tasks, and outperform the baselines in both reward learning and reward optimization.
more » « less- NSF-PAR ID:
- 10473121
- Publisher / Repository:
- SAGE Publications
- Date Published:
- Journal Name:
- The International Journal of Robotics Research
- Volume:
- 43
- Issue:
- 5
- ISSN:
- 0278-3649
- Format(s):
- Medium: X Size: p. 665-684
- Size(s):
- ["p. 665-684"]
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
This paper presents a framework to learn the reward function underlying high-level sequential tasks from demonstrations. The purpose of reward learning, in the context of learning from demonstration (LfD), is to generate policies that mimic the demonstrator’s policies, thereby enabling imitation learning. We focus on a human-robot interaction(HRI) domain where the goal is to learn and model structured interactions between a human and a robot. Such interactions can be modeled as a partially observable Markov decision process (POMDP) where the partial observability is caused by uncertainties associated with the ways humans respond to different stimuli. The key challenge in finding a good policy in such a POMDP is determining the reward function that was observed by the demonstrator. Existing inverse reinforcement learning(IRL) methods for POMDPs are computationally very expensive and the problem is not well understood. In comparison, IRL algorithms for Markov decision process (MDP) are well defined and computationally efficient. We propose an approach of reward function learning for high-level sequential tasks from human demonstrations where the core idea is to reduce the underlying POMDP to an MDP and apply any efficient MDP-IRL algorithm. Our extensive experiments suggest that the reward function learned this way generates POMDP policies that mimic the policies of the demonstrator well.more » « less
-
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 letter, 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.more » « less
-
more » « less
We propose a structured prediction approach for robot imitation learning from demonstrations. Among various tools for robot imitation learning, supervised learning has been observed to have a prominent role. Structured prediction is a form of supervised learning that enables learning models to operate on output spaces with complex structures. Through the lens of structured prediction, we show how robots can learn to imitate trajectories belonging to not only Euclidean spaces but also Riemannian manifolds. Exploiting ideas from information theory, we propose a class of loss functions based on the f-divergence to measure the information loss between the demonstrated and reproduced probabilistic trajectories. Different types of f-divergence will result in different policies, which we call imitation modes. Furthermore, our approach enables the incorporation of spatial and temporal trajectory modulation, which is necessary for robots to be adaptive to the change in working conditions. We benchmark our algorithm against state-of-the-art methods in terms of trajectory reproduction and adaptation. The quantitative evaluation shows that our approach outperforms other algorithms regarding both accuracy and efficiency. We also report real-world experimental results on learning manifold trajectories in a polishing task with a KUKA LWR robot arm, illustrating the effectiveness of our algorithmic framework.
-
In this paper, we develop a novel and safe control design approach that takes demonstrations provided by a human teacher to enable a robot to accomplish complex manipulation scenarios in dynamic environments. First, an overall task is divided into multiple simpler subtasks that are more appropriate for learning and control objectives. Then, by collecting human demonstrations, the subtasks that require robot movement are modeled by probabilistic movement primitives (ProMPs). We also study two strategies for modifying the ProMPs to avoid collisions with environmental obstacles. Finally, we introduce a rule-base control technique by utilizing a finite-state machine along with a unique means of control design for ProMPs. For the ProMP controller, we propose control barrier and Lyapunov functions to guide the system along a trajectory within the distribution defined by a ProMP while guaranteeing that the system state never leaves more than a desired distance from the distribution mean. This allows for better performance on nonlinear systems and offers solid stability and known bounds on the system state. A series of simulations and experimental studies demonstrate the efficacy of our approach and show that it can run in real time. Note to Practitioners —This paper is motivated by the need to create a teach-by-demonstration framework that captures the strengths of movement primitives and verifiable, safe control. We provide a framework that learns safe control laws from a probability distribution of robot trajectories through the use of advanced nonlinear control that incorporates safety constraints. Typically, such distributions are stochastic, making it difficult to offer any guarantees on safe operation. Our approach ensures that the distribution of allowed robot trajectories is within an envelope of safety and allows for robust operation of a robot. Furthermore, using our framework various probability distributions can be combined to represent complex scenarios in the environment. It will benefit practitioners by making it substantially easier to test and deploy accurate, efficient, and safe robots in complex real-world scenarios. The approach is currently limited to scenarios involving static obstacles, with dynamic obstacle avoidance an avenue of future effort.more » « less
