Full-Body Optimal Control Toward Versatile and Agile Behaviors in a Humanoid Robot

Ishihara, Koji; Itoh, Takeshi; Morimoto, Jun

doi:10.1109/lra.2019.2947001

Cited by 27 publications

(6 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach assumes a cost functional, which is minimised during motor action. This is very suitable for robotic applications [36,63]. Inverse optimal control can be used to circumvent the assumption of the cost functional by inferring it from the data.…”

Section: Introductionmentioning

confidence: 99%

Modelling and analysis of Parkinsonian gait

Unni

Menon

2022

Nonlinear Dyn

View full text Add to dashboard Cite

Freezing of gait is a late-stage debilitating symptom of Parkinson’s disease (PD) characterised by a sudden involuntary stoppage of forward progression of gait. The present understanding of PD gait is limited, and there is a need to develop mathematical models explaining PD gait’s underlying mechanisms. A novel hybrid system model is proposed in this paper, in which a mechanical model is coupled with a neuronal model. The proposed hybrid system model has event-dependent feedback and demonstrates PD-relevant behaviours such as freezing, high variability and stable gait. The model’s robustness is studied by analysing relevant parameters such as gain in the event-dependent feedback and level of activation of the central pattern generator neurons. The effect of augmented feedback on the model is also studied to understand different FoG management methods, such as sensory and auditory cues. The model indicates the frequency-dependent behaviours in PD, which are in line with the STN stimulation and external cueing-related studies. The model allows one to estimate the parameters from the data and thereby personalise the cueing regimes for patients. The model can be of help in understanding the mechanism of FoG and developing measures to counter its severity.

show abstract

Section: Introductionmentioning

confidence: 99%

Modelling and analysis of Parkinsonian gait

Unni

Menon

2022

Nonlinear Dyn

View full text Add to dashboard Cite

show abstract

“…In [6], the constrained dynamics is explicitly solved in the context of trajectory optimization. In [24], a hierarchical trajectory optimization is also inverting directly the constrained system with real-time applications. In [33], a similar approach is used and extended to account for constrained impact dynamics and switching constraints.…”

Section: Introductionmentioning

confidence: 99%

Proximal and Sparse Resolution of Constrained Dynamic Equations

Carpentier¹,

Budhiraja²,

Mansard³

2021

Robotics: Science and Systems XVII

View full text Add to dashboard Cite

Control of robots with kinematic constraints like loop-closure constraints or interactions with the environment requires solving the underlying constrained dynamics equations of motion. Several approaches have been proposed so far in the literature to solve these constrained optimization problems, for instance by either taking advantage in part of the sparsity of the kinematic tree or by considering an explicit formulation of the constraints in the problem resolution. Yet, not all the constraints allow an explicit formulation and in general, approaches of the state of the art suffer from singularity issues, especially in the context of redundant or singular constraints. In this paper, we propose a unified approach to solve forward dynamics equations involving constraints in an efficient, generic and robust manner. To this aim, we first (i) propose a proximal formulation of the constrained dynamics which converges to an optimal solution in the least-square sense even in the presence of singularities. Based on this proximal formulation, we introduce (ii) a sparse Cholesky factorization of the underlying Karush-Kuhn-Tucker matrix related to the constrained dynamics, which exploits at best the sparsity of the kinematic structure of the robot. We also show (iii) that it is possible to extract from this factorization the Cholesky decomposition associated to the so-called Operational Space Inertia Matrix, inherent to task-based control frameworks or physic simulations. These new formulation and factorization, implemented within the Pinocchio library, are benchmark on various robotic platforms, ranging from classic robotic arms or quadrupeds to humanoid robots with closed kinematic chains, and show how they significantly outperform alternative solutions of the state of the art by a factor 2 or more.

show abstract

“…Based on these constraints, an abstract model is designed instead of a real whole body dynamics model [1,2,3,4,5,6,7,8]. It should be mentioned that several studies exist where a whole body dynamics model is developed [9,10,11]. In the second point of view, the core of the framework is a set of signal generators which are coupled together to generate endogenously rhythmic signals [12,13,14,15].…”

Section: Introductionmentioning

confidence: 99%

Robust Biped Locomotion Using Deep Reinforcement Learning on Top of an Analytical Control Approach

Kasaei,

Abreu,

Lau

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper proposes a modular framework to generate robust biped locomotion using a tight coupling between an analytical walking approach and deep reinforcement learning. This framework is composed of six main modules which are hierarchically connected to reduce the overall complexity and increase its flexibility. The core of this framework is a specific dynamics model which abstracts a humanoid's dynamics model into two masses for modeling upper and lower body. This dynamics model is used to design an adaptive reference trajectories planner and an optimal controller which are fully parametric. Furthermore, a learning framework is developed based on Genetic Algorithm (GA) and Proximal Policy Optimization (PPO) to find the optimum parameters and to learn how to improve the stability of the robot by moving the arms and changing its center of mass (COM) height. A set of simulations are performed to validate the performance of the framework using the official RoboCup 3D League simulation environment. The results validate the performance of the framework, not only in creating a fast and stable gait but also in learning to improve the upper body efficiency.

show abstract

Full-Body Optimal Control Toward Versatile and Agile Behaviors in a Humanoid Robot

Cited by 27 publications

References 28 publications

Modelling and analysis of Parkinsonian gait

Modelling and analysis of Parkinsonian gait

Proximal and Sparse Resolution of Constrained Dynamic Equations

Robust Biped Locomotion Using Deep Reinforcement Learning on Top of an Analytical Control Approach

Contact Info

Product

Resources

About