Using Sensorimotor Contingencies for Terrain Discrimination and Adaptive Walking Behavior in the Quadruped Robot Puppy

Hoffmann, Matej; Schmidt, Nico M.; Pfeifer, Rolf; Engel, Andreas K.; Maÿe, Alexander

doi:10.1007/978-3-642-33093-3_6

Cited by 16 publications

(16 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Consequently there is a gap between the performance on the train set and the performance on the test set. This demonstrates the correlation of terrain classification performance and the actions of the robot, confirming the findings in [5].…”

Section: B System Classification Scoresupporting

confidence: 84%

See 1 more Smart Citation

Terrain Classification for a Quadruped Robot

Degrave

Cauwenbergh²,

wyffels

et al. 2013

2013 12th International Conference on Machine Learning and Applications

View full text Add to dashboard Cite

Abstract-Using data retrieved from the Puppy II robot at the University of Zurich (UZH), we show that machine learning techniques with non-linearities and fading memory are effective for terrain classification, both supervised and unsupervised, even with a limited selection of input sensors. The results indicate that most information for terrain classification is found in the combination of tactile sensors and proprioceptive joint angle sensors. The classification error is small enough to have a robot adapt the gait to the terrain and hence move more robustly.

show abstract

Section: B System Classification Scoresupporting

confidence: 84%

“…Furthermore has it been shown for quadruped robots that force-sensing in the legs and current-use in the motors deliver reasonable results upon processing with an Adaboost algorithm [4]. Even only using proprioceptive and contact sensors proved effective in ground discrimination [5].…”

Section: Introductionmentioning

confidence: 99%

Terrain Classification for a Quadruped Robot

Degrave

Cauwenbergh²,

wyffels

et al. 2013

2013 12th International Conference on Machine Learning and Applications

View full text Add to dashboard Cite

show abstract

“…Similar implications apply to other sensory modalities. For example, a quadruped robot running on different ground is critically able to improve terrain discrimination if a history of the actions taken (gaits used) is considered together with sensory stimulations induced in tactile, proprioceptive, and inertial sensors (Hoffmann et al 2012). …”

Section: Action In Robotic Perceptionmentioning

confidence: 99%

Implications of Action-Oriented Paradigm Shifts in Cognitive Science

et al. 2016

Self Cite

View full text Add to dashboard Cite

An action-oriented perspective changes the role of an individual from a passive observer to an actively engaged agent interacting in a closed loop with the world as well as with others. Cognition exists to serve action within a landscape that contains both. This chapter surveys this landscape and addresses the status of the pragmatic turn. Its potential infl uence on science and the study of cognition are considered (including perception, social cognition, social interaction, sensorimotor entrainment, and language acquisition) and its impact on how neuroscience is studied is also investigated (with the notion that brains do not passively build models, but instead support the guidance of action).A review of its implications in robotics and engineering includes a discussion of the application of enactive control principles to couple action and perception in robotics as well as the conceptualization of system design in a more holistic, less modular manner. Practical applications that can impact the human condition are reviewed (e.g., educational applications, treatment possibilities for developmental and psychopathological disorders, the development of neural prostheses). All of this foreshadows the potential societal implications of the pragmatic turn. The chapter concludes that an action-oriented approach emphasizes a continuum of interaction between technical aspects of cognitive systems and robotics, biology, psychology, the social sciences, and the humanities, where the individual is part of a grounded cultural system.

show abstract

“…The author varied the window size in the initial experiments, but the shorter length increased the classifier complexity (random forest size) without any gain in the accuracy. Similar to the this size, Hoffman et al [7] found the 6 seconds-long sensor readings the most accurate with their four-legged robot and an other work [5] concluded the 4 seconds-long window over 1 second. However, shorter windows can suit better for different robots or gaits; Bermudez et al [1] found a 350 msec time window enough for a running hexapod robot to maximize the model accuracy.…”

Section: Sample Collectionmentioning

confidence: 68%

“…This result outperformed all training times in [16], considering the weaker processor and the larger training set (12373 vs. 9203 samples in [16]) of this paper. The feature extraction with three FFT analyses took 3 msec on a MIPS CPU (576 Mhz) in AIBO and a smaller forest (rf 7,5 ) with 90.9% accuracy was selected because of the trade-offs in embedded platforms. This smaller RF predicted a surface in 20-90 ìsec with 833KB RAM.…”

Section: Computational Requirementsmentioning

confidence: 99%

Rigidity-Based Surface Recognition for a Domestic Legged Robot

Kertész¹

2016

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Abstract-Although the infrared (IR) range and motor force sensors have been rarely applied to the surface recognition of mobile robots, they are fused in this paper with accelerometer and ground contact force sensors to distinguish six indoor surface types. Their sensor values are affected by the crawling gait period, therefore, certain components of the fast Fourier transform over these data are included in the feature vectors as well as remarkable discriminative power is observed for the same scalar statistics of different sensing modalities. The machine learning aspects are analyzed with random forests (RF) because of their stable performance and some inherent, beneficial properties for the model development process. The robustness is evaluated with unseen data after the model accuracy is estimated with cross-validation (CV), and regardless whether a Sony ERS-7 walks barefoot or wears socks, the forests achieve 94% accuracy. This result outperforms the state of the art techniques for indoor surfaces in the literature and the classification execution is real-time on the robot. The above mentioned model development process with RF is documented to create new models for other robots more quickly and efficiently.

show abstract

Using Sensorimotor Contingencies for Terrain Discrimination and Adaptive Walking Behavior in the Quadruped Robot Puppy

Cited by 16 publications

References 16 publications

Terrain Classification for a Quadruped Robot

Terrain Classification for a Quadruped Robot

Implications of Action-Oriented Paradigm Shifts in Cognitive Science

Rigidity-Based Surface Recognition for a Domestic Legged Robot

Contact Info

Product

Resources

About