Quantifying teaching behavior in robot learning from demonstration

Sena, Aran; Howard, Matthew

doi:10.1177/0278364919884623

Cited by 36 publications

(31 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, the proposed approach is first examined through a toy experiment, then a more complex 3-link planar system, before evaluating its performance in the context of programming by demonstration with a human demonstrator and a 7DoF physical robot. 2…”

Section: Discussionmentioning

confidence: 99%

“…In recent years, there has been a booming shift in the development of versatile, autonomous robots capable of performing increasingly complex tasks. Such robots are expected to enhance the capabilities of ordinary people to introduce automation into their lives by means of intuitively teaching robots task-oriented behaviour by demonstration [1], [2].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Exploiting Ergonomic Priors in Human-to-Robot Task Transfer

Manavalan,

Ray,

Howard

2020

Preprint

Self Cite

View full text Add to dashboard Cite

In recent years, there has been a booming shift in the development of versatile, autonomous robots by introducing means to intuitively teach robots task-oriented behaviour by demonstration. In this paper, a method based on programming by demonstration is proposed to learn null space policies from constrained motion data. The main advantage to using this is generalisation of a task by retargeting a systems redundancy as well as the capability to fully replace an entire system with another of varying link number and lengths while still accurately repeating a task subject to the same constraints. The effectiveness of the method has been demonstrated in a 3-link simulation and a real world experiment using a human subject as the demonstrator and is verified through task reproduction on a 7DoF physical robot. In simulation, the method works accurately with even as little as five data points producing errors less than 10 −14 . The approach is shown to outperform the current state-of-the-art approach in a simulated 3DoF robot manipulator control problem where motions are reproduced using learnt constraints. Retargeting of a systems null space component is also demonstrated in a task where controlling how redundancy is resolved allows for obstacle avoidance. Finally, the approach is verified in a real world experiment using demonstrations from a human subject where the learnt task space trajectory is transferred onto a 7DoF physical robot of a different embodiment.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Exploiting Ergonomic Priors in Human-to-Robot Task Transfer

Manavalan,

Ray,

Howard

2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…By combining kinesthetic teaching with a graphical user interface (GUI) that guides the user throughout the entire teaching process, we present an intuitive interface that maximally supports novice users. As shown in [9], the additional feedback loop through combination of execution and teaching, closes the gap between the user's assumed and the robot's actual task knowledge, which further improves the teaching performance.…”

Section: Introductionmentioning

confidence: 97%

Collaborative Programming of Conditional Robot Tasks

Willibald

Eiband

Lee

2020

2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Conventional robot programming methods are not suited for non-experts to intuitively teach robots new tasks. For this reason, the potential of collaborative robots for production cannot yet be fully exploited. In this work, we propose an active learning framework, in which the robot and the user collaborate to incrementally program a complex task. Starting with a basic model, the robot's task knowledge can be extended over time if new situations require additional skills. An on-line anomaly detection algorithm therefore automatically identifies new situations during task execution by monitoring the deviation between measured-and commanded sensor values. The robot then triggers a teaching phase, in which the user decides to either refine an existing skill or demonstrate a new skill. The different skills of a task are encoded in separate probabilistic models and structured in a high-level graph, guaranteeing robust execution and successful transition between skills. In the experiments, our approach is compared to two state-of-the-art Programming by Demonstration frameworks on a real system. Increased intuitiveness and task performance of the method can be shown, allowing shop-floor workers to program industrial tasks with our framework.

show abstract

“…this limitation is to provide the user with some feedback, such as a visual illustration of what the robot has currently learned [8]. Yet, such an approach requires the appropriate design of a feedback mechanism, which might not be trivial in a highdimensional task, and still requires the user to choose the demonstration eventually.…”

Section: Introductionmentioning

confidence: 99%

Active Learning of Bayesian Probabilistic Movement Primitives

Kulak

Girgin

Odobez

et al. 2021

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Learning from Demonstration permits non-expert users to easily and intuitively reprogram robots. Among approaches embracing this paradigm, probabilistic movement primitives (ProMPs) are a well-established and widely used method to learn trajectory distributions. However, providing or requesting useful demonstrations is not easy, as quantifying what constitutes a good demonstration in terms of generalization capabilities is not trivial. In this paper, we propose an active learning method for contextual ProMPs for addressing this problem. More specifically, we learn the trajectory distributions using a Bayesian Gaussian mixture model (BGMM) and then leverage the notion of epistemic uncertainties to iteratively choose new context query points for demonstrations. We show that this approach reduces the required number of human demonstrations. We demonstrate the effectiveness of the approach on a pouring task, both in simulation and on a real 7-DoF Franka Emika robot.

show abstract

Quantifying teaching behavior in robot learning from demonstration

Cited by 36 publications

References 47 publications

Exploiting Ergonomic Priors in Human-to-Robot Task Transfer

Exploiting Ergonomic Priors in Human-to-Robot Task Transfer

Collaborative Programming of Conditional Robot Tasks

Active Learning of Bayesian Probabilistic Movement Primitives

Contact Info

Product

Resources

About