Multi-robot transfer learning: A dynamical system perspective

Helwa, Mohamed K.; Schoellig, Angela P.

doi:10.1109/iros.2017.8206342

Cited by 32 publications

(30 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Remark 3. If the source and target systems have underlying L 1 adaptive controllers with different reference models, then it is still possible to implement the multi-robot framework by using the reference models to build a map from the source system to the target system [6]. Using this map, trajectories learned on the source system can be transferred to the target system, which has a different reference model.…”

Section: A Multi-robot Transfermentioning

confidence: 99%

“…In [5], a preliminary study of transfer learning between two nonlinear, unicycle robots is presented. In [6], it is proved that the optimal transfer learning map between two robots is, in general, a dynamic system. An algorithm is also provided for determining the properties of the optimal dynamic map, including its order, relative degree and the variables it depends on.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data-Efficient Multirobot, Multitask Transfer Learning for Trajectory Tracking

Pereida

Helwa

Schoellig

2018

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

Transfer learning has the potential to reduce the burden of data collection and to decrease the unavoidable risks of the training phase. In this paper, we introduce a multi-robot, multi-task transfer learning framework that allows a system to complete a task by learning from a few demonstrations of another task executed on another system. We focus on the trajectory tracking problem where each trajectory represents a different task, since many robotic tasks can be described as a trajectory tracking problem. The proposed, multi-robot transfer learning framework is based on a combined L1 adaptive control and iterative learning control approach. The key idea is that the adaptive controller forces dynamically different systems to behave as a specified reference model. The proposed multi-task transfer learning framework uses theoretical control results (e.g., the concept of vector relative degree) to learn a map from desired trajectories to the inputs that make the system track these trajectories with high accuracy. This map is used to calculate the inputs for a new, unseen trajectory. Experimental results using two different quadrotor platforms and six different trajectories show that, on average, the proposed framework reduces the first-iteration tracking error by 74% when information from tracking a different, single trajectory on a different quadrotor is utilized.

show abstract

Section: A Multi-robot Transfermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Data-Efficient Multirobot, Multitask Transfer Learning for Trajectory Tracking

Pereida

Helwa

Schoellig

2018

IEEE Robot. Autom. Lett.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Machine learning techniques have been applied to many robot control problems with the goal of achieving high performance in the presence of uncertainties in the dynamics and the environment [1]. Due to the cost associated with data collection and training, approaches such as manifold alignment [2]- [4] and learning invariant features [5], [6] have been proposed to transfer knowledge between robots and thereby increase the efficiency of robot learning. In these approaches, datasets on a set of sample tasks are initially collected from both robots.…”

Section: Introductionmentioning

confidence: 99%

Knowledge Transfer Between Robots with Similar Dynamics for High-Accuracy Impromptu Trajectory Tracking

Zhou

Helwa

Schoellig

et al. 2019

2019 18th European Control Conference (ECC)

Self Cite

View full text Add to dashboard Cite

In this paper, we propose an online learning approach that enables the inverse dynamics model learned for a source robot to be transferred to a target robot (e.g., from one quadrotor to another quadrotor with different mass or aerodynamic properties). The goal is to leverage knowledge from the source robot such that the target robot achieves highaccuracy trajectory tracking on arbitrary trajectories from the first attempt with minimal data recollection and training. Most existing approaches for multi-robot knowledge transfer are based on post-analysis of datasets collected from both robots. In this work, we study the feasibility of impromptu transfer of models across robots by learning an error prediction module online. In particular, we analytically derive the form of the mapping to be learned by the online module for exact tracking, propose an approach for characterizing similarity between robots, and use these results to analyze the stability of the overall system. The proposed approach is illustrated in simulation and verified experimentally on two different quadrotors performing impromptu trajectory tracking tasks, where the quadrotors are required to accurately track arbitrary hand-drawn trajectories from the first attempt.

show abstract

“…Transfer learning helps to bridge this gap by providing faster learning of activities and better collaboration of assistive robots in AAL environments (Helwa and Schoellig 2017). A conceptual overview of the processes involved in learning of human activities for assistive robotics is given in Fig.…”

Section: Introductionmentioning

confidence: 99%

Human activity learning for assistive robotics using a classifier ensemble

et al. 2018

View full text Add to dashboard Cite

Assistive robots in ambient assisted living environments can be equipped with learning capabilities to effectively learn and execute human activities. This paper proposes a human activity learning (HAL) system for application in assistive robotics. An RGB-depth sensor is used to acquire information of human activities, and a set of statistical, spatial and temporal features for encoding key aspects of human activities are extracted from the acquired information of human activities. Redundant features are removed and the relevant features used in the HAL model. An ensemble of three individual classifiers-support vector machines (SVMs), K -nearest neighbour and random forest-is employed to learn the activities. The performance of the proposed system is improved when compared with the performance of other methods using a single classifier. This approach is evaluated on experimental dataset created for this work and also on a benchmark dataset-the Cornell Activity Dataset (CAD-60). Experimental results show the overall performance achieved by the proposed system is comparable to the state of the art and has the potential to benefit applications in assistive robots for reducing the time spent in learning activities.

show abstract

Multi-robot transfer learning: A dynamical system perspective

Cited by 32 publications

References 26 publications

Data-Efficient Multirobot, Multitask Transfer Learning for Trajectory Tracking

Data-Efficient Multirobot, Multitask Transfer Learning for Trajectory Tracking

Knowledge Transfer Between Robots with Similar Dynamics for High-Accuracy Impromptu Trajectory Tracking

Human activity learning for assistive robotics using a classifier ensemble

Contact Info

Product

Resources

About