“…In this section, we developed a new PNEM algorithm to maximize the log-likelihood function (12). In addition, we devised a new positive and negative demonstration-based Kmeans (PNKmeans) algorithm for determining the initial value for PNEM.…”
Section: Main Algorithms Of Pndmpmentioning
confidence: 99%
“…Particularly, some researchers have utilized them to filter the nonexpert demonstrations as a preprocessing step for motion models. 11,12 However, to the best of the authors’ knowledge, few studies have sought to directly improve DMP with negative demonstrations.…”
Dynamic motion primitive has been the most prevalent model-based imitation learning method in the last few decades. Gaussian mixed regression dynamic motion primitive, which draws upon the strengths of both the motion model and the probability model to cope with multiple demonstrations, is a very practical and conspicuous branch in the dynamic motion primitive family. As Gaussian mixed regression dynamic motion primitive only learns from expert demonstrations and requires full environmental information, it is incapable of handling tasks with unmodeled obstacles. Aiming at this problem, we proposed the positive and negative demonstrations-based dynamic motion primitive, for which the introduction of negative demonstrations can bring additional flexibility. Positive and negative demonstrations-based dynamic motion primitive extends Gaussian mixed regression dynamic motion primitive in three aspects. The first aspect is a new maximum log-likelihood function that balances the probabilities on positive and negative demonstrations. The second one is the positive and negative demonstrations-based expectation–maximum, which involves iteratively calculating the lower bound of a new Q-function. And the last is the application framework of data set aggregation for positive and negative demonstrations-based dynamic motion primitive to handle unmodeled obstacles. Experiments on several typical robot manipulating tasks, which include letter writing, obstacle avoidance, and grasping in a grid box, are conducted to validate the performance of positive and negative demonstrations-based dynamic motion primitive.
“…In this section, we developed a new PNEM algorithm to maximize the log-likelihood function (12). In addition, we devised a new positive and negative demonstration-based Kmeans (PNKmeans) algorithm for determining the initial value for PNEM.…”
Section: Main Algorithms Of Pndmpmentioning
confidence: 99%
“…Particularly, some researchers have utilized them to filter the nonexpert demonstrations as a preprocessing step for motion models. 11,12 However, to the best of the authors’ knowledge, few studies have sought to directly improve DMP with negative demonstrations.…”
Dynamic motion primitive has been the most prevalent model-based imitation learning method in the last few decades. Gaussian mixed regression dynamic motion primitive, which draws upon the strengths of both the motion model and the probability model to cope with multiple demonstrations, is a very practical and conspicuous branch in the dynamic motion primitive family. As Gaussian mixed regression dynamic motion primitive only learns from expert demonstrations and requires full environmental information, it is incapable of handling tasks with unmodeled obstacles. Aiming at this problem, we proposed the positive and negative demonstrations-based dynamic motion primitive, for which the introduction of negative demonstrations can bring additional flexibility. Positive and negative demonstrations-based dynamic motion primitive extends Gaussian mixed regression dynamic motion primitive in three aspects. The first aspect is a new maximum log-likelihood function that balances the probabilities on positive and negative demonstrations. The second one is the positive and negative demonstrations-based expectation–maximum, which involves iteratively calculating the lower bound of a new Q-function. And the last is the application framework of data set aggregation for positive and negative demonstrations-based dynamic motion primitive to handle unmodeled obstacles. Experiments on several typical robot manipulating tasks, which include letter writing, obstacle avoidance, and grasping in a grid box, are conducted to validate the performance of positive and negative demonstrations-based dynamic motion primitive.
“…Multiple robot systems can transport the deformable object cooperatively by tracking the coupled DMP trajectory. Evolved from the original DMP algorithm [1], several works have been done to extend its applicability by incorporating different techniques, such as reinforcement learning [2], [3], statistical generalization [4] and the combination of obstacle avoidance algorithms [5], [6]. A temporal coupling algorithm was developed to handle velocity and acceleration constraints for solely DMP trajectories [7].…”
Dynamic Movement Primitives (DMP) are widely applied in movement representation due to their ability to encode tasks using generalization properties. However, the coupled multiple DMP generalization cannot be directly solved based on the original DMP formula. Prior works provide satisfactory performance for the coupled DMP generalization in rigid object manipulation, but their extension to deformable objects may degrade due to the intrinsic uncertainty of the deformable model structure and parameters. This paper introduces an adaptive term to replace the fixed term to couple multiple DMP generalizations and model the deformable object using the classic mass-spring-damper model. Based on the modeling, the manipulation of a deformable object can be treated as a second-order system, which provides additional implementation flexibility and robustness in deformable object transportation. To validate the proposed method, we perform extensive simulations for cooperatively transporting a rope and a deformable thin film, imitating the manipulation with a semi-ellipse trajectory and M-shape trajectory. We further implement our method on a dual-arm robot platform for rope manipulation with depth visual feedback. Both simulation and experiment results demonstrate satisfactory DMP generalization, collision avoidance, and configuration preservation.
“…For this purpose, controllers that can generate real-time motion trajectories are highly sought. Among them, non-linear model predictive controllers (MPC) [4], [5] can provide real-time computations [3], reactive control [6], [7], and because of optimal control over a time horizon, can deal with disturbances and perturbations to the system [8].…”
As locomotion decisions must be taken by considering the future, most existing quadruped controllers are based on a model predictive controller (MPC) with a reduced model of the dynamics to generate the motion and a wholebody controller to execute it. Yet the simplifying assumptions of the MPC are often chosen ad-hoc or by intuition. In this article, we focus on a set of MPCs and analyze the effect of chosen model reductions on the behavior of the robot. Based on existing formulations, we present additional controllers to better understand the influence of model reductions on the controller capabilities. Finally, we propose a robust predictive controller capable of optimizing the foot placements, gait period, centerof-mass trajectory and ground reaction forces. The behavior of these controllers is statistically evaluated in simulation. This empirical study aims to assess the relative importance of the components of the optimal control problem (variables, costs, dynamics) to be able to take reasoned decisions instead of arbitrarily emphasizing or neglecting some of them. We also provide a qualitative study in simulation and on the real robot Solo-12.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.