A Neural Architecture for Performing Actual and Mentally Simulated Movements During Self-Intended and Observed Bimanual Arm Reaching Movements

Gentili, Rodolphe J.; Oh, Hyuk; Huang, Di-Wei; Katz, Garrett E.; Miller, Ross H.; Reggia, James A.

doi:10.1007/s12369-014-0276-5

Cited by 14 publications

(15 citation statements)

References 105 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The joint angle trajectory appears to be overall smooth and sigmoid-shaped, and the velocity profiles are single-peaked and near bell-shaped. This is comparable to and consistent with the results in past studies focusing on human arm movements, which suggests that joint trajectories are highly stereotyped and contain invariant spatio-temporal features including sigmoid joint displacement and bell-shaped velocity profiles [14,15].…”

Section: Arm Performance and Trajectorysupporting

confidence: 91%

“…where weights b have been used in past neural models to control the degree in which a motor plan is converted to actions, the mechanism of which is believed to be related to the basal ganglia or the prefrontal cortex [15]. In early iterations, influences of both subsystems increase, with the open-loop subsystem rising more rapidly and contributing more.…”

Section: Motor Output Filtermentioning

confidence: 99%

See 1 more Smart Citation

A limit-cycle self-organizing map architecture for stable arm control

et al. 2017

Self Cite

View full text Add to dashboard Cite

Inspired by the oscillatory nature of cerebral cortex activity, we recently proposed and studied self-organizing maps (SOMs) based on limit cycle neural activity in an attempt to improve the information efficiency and robustness of conventional single-node, single-pattern representations. Here we explore for the first time the use of limit cycle SOMs to build a neural architecture that controls a robotic arm by solving inverse kinematics in reach-and-hold tasks. This multi-map architecture integrates open-loop and closed-loop controls that learn to self-organize oscillatory neural representations and to harness non-fixed-point neural activity even for fixed-point arm reaching tasks. We show through computer simulations that our architecture generalizes well, achieves accurate, fast, and smooth arm movements, and is robust in the face of arm perturbations, map damage, and variations of internal timing parameters controlling the flow of activity. A robotic implementation is evaluated successfully without further training, demonstrating for the first time that limit cycle maps can control a physical robot arm. We conclude that architectures based on limit cycle maps can be organized to function effectively as neural controllers.

show abstract

Section: Arm Performance and Trajectorysupporting

confidence: 91%

Section: Motor Output Filtermentioning

confidence: 99%

A limit-cycle self-organizing map architecture for stable arm control

et al. 2017

Self Cite

View full text Add to dashboard Cite

show abstract

“…In order to use our robotic learning system to study the CEG, the existing software needs to be converted into neurocomputational form, something that is currently in progress. At present, we have converted the low-level sensorimotor control of individual robot actions into neural network modules, replacing the corresponding original software with a neural architecture, the DIRECT algorithm, that we have previously studied via non-robotic computer simulations (Gentili et al, 2015 ). Testing of the resulting robotic control system (i.e., the top-down symbolic cognitive components plus the neural sensorimotor components instantiated in our robot) on tasks such as maintenance operations on the disk drive dock and pipe-and-valve system described above show that the robot’s behavior with a neural sensorimotor system is virtually unchanged from the original.…”

Section: Bridging the Cegmentioning

confidence: 99%

“…This is particularly relevant to the sensorimotor level of imitation learning. As mentioned above, we replaced traditional low-level motion planning with the DIRECT neural algorithm (Bullock et al, 1993 ; Gentili et al, 2015 ), which learns in an unsupervised fashion using exploratory “babbling.” Much of the robotic motion planning done during imitation learning of maintenance tasks (like those we described above) requires the use of an inverse kinematics solver that determines a joint trajectory for a given end-effector starting position and target. DIRECT learns this coordinate transformation in a self-organizing map architecture by training on a randomly generated set of joint movements and their consequential end-effector transformations.…”

Section: Bridging the Cegmentioning

confidence: 99%

“…We have developed an augmented version of the DIRECT model that controls imitation of coordinated bimanual movements (Gentili et al, 2015 ) to support end-effector orientations, which are critical to performing the demonstrated tasks. This allows the planner to provide joint trajectories that orient the robot’s grippers for fine motor tasks, such as manipulating screws, coordinating exchanges of objects between grippers, and fitting objects into tight spaces.…”

Section: Bridging the Cegmentioning

confidence: 99%

See 1 more Smart Citation

Humanoid Cognitive Robots That Learn by Imitating: Implications for Consciousness Studies

2018

Self Cite

View full text Add to dashboard Cite

While the concept of a conscious machine is intriguing, producing such a machine remains controversial and challenging. Here, we describe how our work on creating a humanoid cognitive robot that learns to perform tasks via imitation learning relates to this issue. Our discussion is divided into three parts. First, we summarize our previous framework for advancing the understanding of the nature of phenomenal consciousness. This framework is based on identifying computational correlates of consciousness. Second, we describe a cognitive robotic system that we recently developed that learns to perform tasks by imitating human-provided demonstrations. This humanoid robot uses cause-effect reasoning to infer a demonstrator's intentions in performing a task, rather than just imitating the observed actions verbatim. In particular, its cognitive components center on top-down control of a working memory that retains the explanatory interpretations that the robot constructs during learning. Finally, we describe our ongoing work that is focused on converting our robot's imitation learning cognitive system into purely neurocomputational form, including both its low-level cognitive neuromotor components, its use of working memory, and its causal reasoning mechanisms. Based on our initial results, we argue that the top-down cognitive control of working memory, and in particular its gating mechanisms, is an important potential computational correlate of consciousness in humanoid robots. We conclude that developing high-level neurocognitive control systems for cognitive robots and using them to search for computational correlates of consciousness provides an important approach to advancing our understanding of consciousness, and that it provides a credible and achievable route to ultimately developing a phenomenally conscious machine.

show abstract

Artificial Companions, Social Bots und Work Bots: Kommunikative Roboter als Forschungsgegenstand der Kommunikations- und Medienwissenschaft

Hepp

2021

Digitaler Strukturwandel Der Öffentlichkeit

View full text Add to dashboard Cite

A Neural Architecture for Performing Actual and Mentally Simulated Movements During Self-Intended and Observed Bimanual Arm Reaching Movements

Cited by 14 publications

References 105 publications

A limit-cycle self-organizing map architecture for stable arm control

A limit-cycle self-organizing map architecture for stable arm control

Humanoid Cognitive Robots That Learn by Imitating: Implications for Consciousness Studies

Artificial Companions, Social Bots und Work Bots: Kommunikative Roboter als Forschungsgegenstand der Kommunikations- und Medienwissenschaft

Contact Info

Product

Resources

About