A novel approach for the generation of complex humanoid walking sequences based on a combination of optimal control and learning of movement primitives

Clever, Debora; Harant, Monika; Koch, Henning; Mombaur, Katja; Endres, Dominik

doi:10.1016/j.robot.2016.06.001

Cited by 21 publications

(26 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently, many different types of MPs have been proposed in literature (Endres et al 2013). These types can be classified as spatial (Giszter et al 1992;Tresch et al 1999), temporal (Clever et al 2016;Endres et al 2013), spatio-temporal (d'Avella et al 2003dynamical MPs (Ijspeert et al 2013).…”

Section: Movement Primitivesmentioning

confidence: 99%

“…Velychko et al (2018) also provide graphical model representations and summarize the features of the MP models presented in this chapter. (Clever et al 2016). Temporal MPs describe the stereotyped temporal patterns of movement parameters (for example EMG, but also joint trajectories as well as endpoint trajectories).…”

Section: Movement Primitivesmentioning

confidence: 99%

“…In general, more MPs allow for more fine-grained temporal structure of the movement, but might lead to over-fitting. To determine the MPs and their number, we follow the approach of Clever et al (2016): weights w and MPs Y q have a Gaussian Process (GP) prior and are learned from the training data by maximizing a variational lower bound on the Bayesian model evidence (ELBO, evidence lower bound). The ELBO is equal to the negative free energy (Friston 2010).…”

Section: Temporal Movement Primitives (Tmp)mentioning

confidence: 99%

See 2 more Smart Citations

Untitled

2019

ACM Trans. Appl. Percept.

View full text Add to dashboard Cite

We compared the perceptual validity of human avatar walking animations driven by six different representations of human movement using a graphics Turing test. All six representations are based on movement primitives (MPs), which are predictive models of full-body movement that differ in their complexity and prediction mechanism. Assuming that humans are experts at perceiving biological movement from noisy sensory signals, it follows that these percepts should be describable by a suitably constructed Bayesian ideal observer model. We build such models from MPs and investigate if the perceived naturalness of human animations are predictable from approximate Bayesian model scores of the MPs. We found that certain MP-based representations are capable of producing movements that are perceptually indistinguishable from natural movements. Furthermore, approximate Bayesian model scores of these representations can be used to predict perceived naturalness. In particular, we could show that movement dynamics are more important for perceived naturalness of human animations than single frame poses. This indicates that perception of human animations is highly sensitive to their temporal coherence. More generally, our results add evidence for a shared MP-representation of action and perception. Even though the motivation of our work is primarily drawn from neuroscience, we expect that our results will be applicable in virtual and augmented reality settings, when perceptually plausible human avatar movements are required.

show abstract

Section: Movement Primitivesmentioning

confidence: 99%

Section: Movement Primitivesmentioning

confidence: 99%

Section: Temporal Movement Primitives (Tmp)mentioning

confidence: 99%

See 1 more Smart Citation

Untitled

2019

ACM Trans. Appl. Percept.

View full text Add to dashboard Cite

show abstract

“…In [16] walking gaits were synthesized via motion primitives [17]. A similar approach is commonly used also in computer graphics [18], [19].…”

Section: Introductionmentioning

confidence: 99%

“…In [16] parametric motion primitives were learned from a dataset of optimized trajectories. Once the motion primitives were defined, their parameters were used as optimization variables to synthesize trajectories not belonging to the original dataset.…”

Section: Introductionmentioning

confidence: 99%

Efficient Walking Gait Generation via Principal Component Representation of Optimal Trajectories: Application to a Planar Biped Robot With Elastic Joints

Gasparri

Manara

Caporale

et al. 2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Recently, the method of choice to exploit robot dynamics for efficient walking is numerical optimization (NO). The main drawback in NO is the computational complexity, which strongly affects the time demand of the solution. Several strategies can be used to make the optimization more treatable and to efficiently describe the solution set. In this work, we present an algorithm to encode effective walking references, generated off-line via numerical optimization, extracting a limited number of principal components and using them as a basis of optimal motions. By combining these components, a good approximation of the optimal gaits can be generated at run time. The advantages of the presented approach are discussed, and an extensive experimental validation is carried out on a planar legged robot with elastic joints. The biped thus controlled is able to start and stop walking on a treadmill, and to control its speed dynamically as the treadmill speed changes.

show abstract

An intelligent navigation of humanoid NAO in the light of classical approach and computational intelligence

Kumar

Mohapatra

Parhi

2018

Computer Animation & Virtual

View full text Add to dashboard Cite

The development of robotics research toward industrialization has created an enhanced demand for modernization of the automation industry. Humanoid robots being advanced than other forms of robots bear a large resemblance to humans and are very much helpful in replacing humans in tedious and repetitive tasks. Therefore, the navigation and path planning of the humanoids bear a large importance in robotics research. The current investigation deals with the path planning of NAO humanoid robots. In the present work, a classical method of regression analysis and an artificial intelligence technique of fuzzy logic are implemented separately for the purpose of obstacle avoidance during the motion of humanoid NAOs toward respective targets. The simulation analysis of the proposed techniques is carried out using V‐REP software. The experiments are performed in laboratory conditions with a proper environment for working of the humanoid NAOs. Finally, a comparison has been made between the simulation and experimental results. The results obtained from the simulation and experimental analyses are in good agreement with each other, which suggest that the proposed methodologies can be used as methods of robust control for the navigation of humanoids.

show abstract

A novel approach for the generation of complex humanoid walking sequences based on a combination of optimal control and learning of movement primitives

Cited by 21 publications

References 36 publications

Untitled

Untitled

Efficient Walking Gait Generation via Principal Component Representation of Optimal Trajectories: Application to a Planar Biped Robot With Elastic Joints

An intelligent navigation of humanoid NAO in the light of classical approach and computational intelligence

Contact Info

Product

Resources

About