Dynamic Density Topological Structure Generation for Real-Time Ladder Affordance Detection

Saputra, Azhar Aulia; Chin, Wei Hong; Toda, Yuichiro; Takesue, Naoyuki; Kubota, Naoyuki

doi:10.1109/iros40897.2019.8968003

Cited by 13 publications

(8 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The robot's external input uses point cloud data instead of visual information, however, this choice of representation does not influence the attention mechanism's implementation. Attention was represented using nodal density in a topological map structure, as had been successfully implemented in our previous research [35]. In this article, we built a dynamic attention model inspired by visual processing processes in nature.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Combining Reflexes and External Sensory Information in a Neuromusculoskeletal Model to Control a Quadruped Robot

Saputra

Botzheim

Ijspeert

et al. 2022

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

This article examines the importance of integrating locomotion and cognitive information for achieving dynamic locomotion from a viewpoint combining biology and ecological psychology. We present a mammalian neuromusculoskeletal model from external sensory information processing to muscle activation, which includes: 1) a visual-attention control mechanism for controlling attention to external inputs; 2) object recognition representing the primary motor cortex; 3) a motor control model that determines motor commands traveling down the corticospinal and reticulospinal tracts; 4) a central pattern generation model representing pattern generation in the spinal cord; and 5) a muscle reflex model representing the muscle model and its reflex mechanism. The proposed model is able to generate the locomotion of a quadruped robot in flat and natural terrain. The experiment also shows the importance of a postural reflex mechanism when experiencing a sudden obstacle. We show the reflex mechanism when a sudden obstacle is separately detected from both external (retina) and internal (touching afferent) sensory information. We present the biological rationale for supporting the proposed model. Finally, we discuss future contributions, trends, and the importance of the proposed research.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The SC receives data from ganglion cells in the retina. We use time-of-flight sensors to provide external sensory information, as in our previous work [34], [35]. The aim of our model is to combine the attention and action which is effectively implemented for sudden obstacle response.…”

Section: A Dynamic Attentionmentioning

confidence: 99%

Combining Reflexes and External Sensory Information in a Neuromusculoskeletal Model to Control a Quadruped Robot

Saputra

Botzheim

Ijspeert

et al. 2022

IEEE Trans. Cybern.

Self Cite

View full text Add to dashboard Cite

show abstract

“…We extended the GNG by adding a dynamic-density model. The algorithm's details are given in (Saputra et al, 2019b) (Saputra et al, 2019a). A comparison between the common GNG and the proposed GNG augmented with dynamic attention can be seen in the link of Video 1.…”

Section: Dynamic-density Topological Map-building With Attention Modelmentioning

confidence: 99%

“…Next, we detect the graspable locations by considering the robot's embodiment. The details of the proposed detection system can be seen in (Saputra et al, 2019a).…”

Section: Affordance Detection For Vertical Laddersmentioning

confidence: 99%

AQuRo: A Cat-like Adaptive Quadruped Robot With Novel Bio-Inspired Capabilities

et al. 2021

Self Cite

View full text Add to dashboard Cite

There are currently many quadruped robots suited to a wide range of applications, but traversing some terrains, such as vertical ladders, remains an open challenge. There is still a need to develop adaptive robots that can walk and climb efficiently. This paper presents an adaptive quadruped robot that, by mimicking feline structure, supports several novel capabilities. We design a novel paw structure and several point-cloud-based sensory structures incorporating a quad-composite time-of-flight sensor and a dual-laser range finder. The proposed robot is equipped with physical and cognitive capabilities which include: 1) a dynamic-density topological map building with attention model, 2) affordance perception using the topological map, and 3) a neural-based locomotion model. The novel capabilities show strong integration between locomotion and internal–external sensory information, enabling short-term adaptations in response to environmental changes. The robot performed well in several situations: walking on natural terrain, walking with a leg malfunction, avoiding a sudden obstacle, climbing a vertical ladder. Further, we consider current problems and future development.

show abstract

“…Moreover, GNG can perform noise reduction [23,24], 3D reconstruction [25][26][27][28] and feature extraction using the topological structure [29,30]. From these reasons, GNG is expected to utilize the unified perceptual system for the point cloud processing [31][32][33][34][35][36][37][38][39]. D. Viejo et al applied GNG-based 3D feature extraction and the matching method to 3D object recognition [40].…”

Section: Introductionmentioning

confidence: 99%

Growing Neural Gas with Different Topologies for 3D Space Perception

et al. 2022

Self Cite

View full text Add to dashboard Cite

Three-dimensional space perception is one of the most important capabilities for an autonomous mobile robot in order to operate a task in an unknown environment adaptively since the autonomous robot needs to detect the target object and estimate the 3D pose of the target object for performing given tasks efficiently. After the 3D point cloud is measured by an RGB-D camera, the autonomous robot needs to reconstruct a structure from the 3D point cloud with color information according to the given tasks since the point cloud is unstructured data. For reconstructing the unstructured point cloud, growing neural gas (GNG) based methods have been utilized in many research studies since GNG can learn the data distribution of the point cloud appropriately. However, the conventional GNG based methods have unsolved problems about the scalability and multi-viewpoint clustering. In this paper, therefore, we propose growing neural gas with different topologies (GNG-DT) as a new topological structure learning method for solving the problems. GNG-DT has multiple topologies of each property, while the conventional GNG method has a single topology of the input vector. In addition, the distance measurement in the winner node selection uses only the position information for preserving the environmental space of the point cloud. Next, we show several experimental results of the proposed method using simulation and RGB-D datasets measured by Kinect. In these experiments, we verified that our proposed method almost outperforms the other methods from the viewpoint of the quantization and clustering errors. Finally, we summarize our proposed method and discuss the future direction on this research.

show abstract

Dynamic Density Topological Structure Generation for Real-Time Ladder Affordance Detection

Cited by 13 publications

References 16 publications

Combining Reflexes and External Sensory Information in a Neuromusculoskeletal Model to Control a Quadruped Robot

Combining Reflexes and External Sensory Information in a Neuromusculoskeletal Model to Control a Quadruped Robot

AQuRo: A Cat-like Adaptive Quadruped Robot With Novel Bio-Inspired Capabilities

Growing Neural Gas with Different Topologies for 3D Space Perception

Contact Info

Product

Resources

About