Inference Through Embodied Simulation in Cognitive Robots

Mohan, Vishwanathan; Morasso, Pietro; Sandini, Giulio; Kasderidis, Stathis

doi:10.1007/s12559-013-9205-4

Cited by 19 publications

(17 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In contrast to direct geometric processing of perceptual and spatial information for reasoning and inference, the proposed framework looks at learning and formation of internal models / memories instead, that are then used to engage in a range of inferences related to feasibility and consequences of the actions of one self or the interacting partner. In this context, the computational approach is motivated by emerging evidence from neurosciences related to embodied simulation (Hesslow 2012;Gallese & Sinigaglia 2011;Mohan et al 2013) in particular: simulation of action: we are able to activate motor structures of the brain in a way that resembles activity during a normal action but does not cause any overt movement (Gallese & Sinigaglia 2011;Grafton 2009); simulation of perception: imagining perceiving something is actually similar to the perceiving it in reality, only di ffe rence be i ng that, the perceptual activity is generated by the brain itself rather than by external stimuli (Barsalou 2011;Grush 2004); anticipation: there exist associative mechanisms that enable both behavioural and perceptual activity to elicit other perceptual activity in the sensory areas of the brain. Most important, a simulated action can elicit perceptual activity that resembles the activity that would have occurred if the action had actually been performed (Barsalou 2011; Hesslow 2012).…”

Section: A Case For Coupled Memory Representations Of Body and Space mentioning

confidence: 99%

“…The episodic memory model to encode multiple sensorimotor experiences of iCub or the resulting bottom-up activations in hubs and the rewards acquired through time, is realized using a recently proposed neural framework for organization of memory in iCub (Mohan et al 2013) that builds up on an excitatory-inhibitory neural network of auto-associative memory (Hopfield 2008). For modeling purposes, the memory network is dealt as a small patch in the sheet-like neocortex, consi sting of 1000 pyramidal cells (N=1000).…”

Section: Representation Of An Experiencementioning

confidence: 99%

“…The construction system controls all the flow of information bottom-up & top-down and execution in the world or in simulation. After the user types in the goal "Assemble Fuse, Holder", the construction system verifies the incoming activity in the object hub due to two sources, perception and user goal using retro-activation (see section 3.2.2 and Mohan et al (2013) for details). If there is no contradi cti on between what the robot expects (top down due to user goal) and what it observes (due to bottom up perception), the construction system is sure that the objects to be acted on are really present in the environment.…”

Section: Example Of Encoding and Recall Of An Experience: Performing mentioning

confidence: 99%

See 2 more Smart Citations

Towards a Brain-like Memory for Cognitive Robots. PhD Dissertation, University of Genova, Genova, Italy

Bhat¹

2018

Preprint

View full text Add to dashboard Cite

The most striking feature of any cognitive system is its ability to keep learning cumulatively and exploit its experiences prospectively to anticipate, reason and produce goal-oriented behaviors. At the core of this intriguing capability lies our memory. Every touch, sound, sight, taste triggers our memory, enabling us to remember and flexibly connect our past experiences, with the available present to the possible future. While emerging trends in neurosciences are rapidly enriching our understanding of the functional organization of memory in the brain, a prospective memory architecture is also a central design feature necessary if robots are to truly become commonplace assistants in numerous application domains (domestic, industrial, others) and in the complexity of the environments we inhabit and create (where neither everything can be known nor can everything be experienced). Hence, with the central premise that cognition is constructive manipulation of memory, this thesis proposes a novel brain guided perspective on the design of cognitive architectures for cumulatively developing systems. Set up in the context of several experiments from animal and infant cognition reenacted on the iCub humanoid, a principled framework for cumulative learning of actions, skills, affordances and cause-effect relations through multiple streams (imitation, exploration, linguistic inputs) is proposed. How such diverse experiences of the robot learnt in past are recalled based on present context, combined with explorative actions to learn something new, creatively connected to generate novel behaviors in the context of sought goals is demonstrated through several tasks. The proposed integrated machinery provides for a shared computational basis for recalling of the past and simulation of the future in line with the emerging trends from neuroscience (like the brain’s default mode network). A notable transition further is the porting of the framework developed on iCub humanoid to real world industrial settings in tasks like assembly and manufacturing (facilitating runtime reasoning and quick switchover to novel assembly tasks). In this sense, the proposed architecture brings together the fields of Robotics, Developmental Psychology, and Neuroscience to craft cognitive and adaptable End User Applications while at the same time provides insights into the functional organization of the brain. In parallel, it lays the foundation for a new generation of cognitive architectures that are domain agnostic (i.e. support open-ended learning), partially embodiment agnostic (i.e. are configurable to new robotic platforms), partially self-driven (i.e. can generate their own internal goals) and brain guided.

show abstract

Section: A Case For Coupled Memory Representations Of Body and Space mentioning

confidence: 99%

Section: Representation Of An Experiencementioning

confidence: 99%

Section: Example Of Encoding and Recall Of An Experience: Performing mentioning

confidence: 99%

See 1 more Smart Citation

Towards a Brain-like Memory for Cognitive Robots. PhD Dissertation, University of Genova, Genova, Italy

Bhat¹

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…At the bottom is the sensory layer to analyse properties of the objects; in particular colour, shape, size and weight. Word information is an additional input coming from the teacher either to issue user goals or teach names of new objects [ 45 ]. Information coming from the sensory layer is projected bottom-up to a set of growing self-organizing maps (SOMs [ 39 ]), organized in a property-specific fashion.…”

Section: Computational Modelmentioning

confidence: 99%

Humanoid infers Archimedes' principle: understanding physical relations and object affordances through cumulative learning experiences

Bhat¹,

Mohan²,

Sandini³

et al. 2016

J. R. Soc. Interface.

Self Cite

View full text Add to dashboard Cite

Emerging studies indicate that several species such as corvids, apes and children solve ‘The Crow and the Pitcher’ task (from Aesop's Fables) in diverse conditions. Hidden beneath this fascinating paradigm is a fundamental question: by cumulatively interacting with different objects, how can an agent abstract the underlying cause–effect relations to predict and creatively exploit potential affordances of novel objects in the context of sought goals? Re-enacting this Aesop's Fable task on a humanoid within an open-ended ‘learning–prediction–abstraction’ loop, we address this problem and (i) present a brain-guided neural framework that emulates rapid one-shot encoding of ongoing experiences into a long-term memory and (ii) propose four task-agnostic learning rules (elimination, growth, uncertainty and status quo) that correlate predictions from remembered past experiences with the unfolding present situation to gradually abstract the underlying causal relations. Driven by the proposed architecture, the ensuing robot behaviours illustrated causal learning and anticipation similar to natural agents. Results further demonstrate that by cumulatively interacting with few objects, the predictions of the robot in case of novel objects converge close to the physical law, i.e. the Archimedes principle: this being independent of both the objects explored during learning and the order of their cumulative exploration.

show abstract

“…1 Results of perceptual analysis activate various neural maps (property-specific SOMs in layer 1), ultimately leading to a distributed representation of the perceived object in the connector hub. (Interested readers may refer to Mohan, Morasso, Sandini, & Kasderidis, 2013, for a detailed description of the sensorimotor organization and learning). The kind of distributed property-specific organization and global integration through hubs is in line with emerging results from neuroscience discussed in section 1.1.…”

Section: The Icub Humanoid and The Underlying The Perception-actionmentioning

confidence: 99%

A Neural Framework for Organization and Flexible Utilization of Episodic Memory in Cumulatively Learning Baby Humanoids

2014

Self Cite

View full text Add to dashboard Cite

Cumulatively developing robots offer a unique opportunity to reenact the constant interplay between neural mechanisms related to learning, memory, prospection, and abstraction from the perspective of an integrated system that acts, learns, remembers, reasons, and makes mistakes. Situated within such interplay lie some of the computationally elusive and fundamental aspects of cognitive behavior: the ability to recall and flexibly exploit diverse experiences of one's past in the context of the present to realize goals, simulate the future, and keep learning further. This article is an adventurous exploration in this direction using a simple engaging scenario of how the humanoid iCub learns to construct the tallest possible stack given an arbitrary set of objects to play with. The learning takes place cumulatively, with the robot interacting with different objects (some previously experienced, some novel) in an open-ended fashion. Since the solution itself depends on what objects are available in the "now," multiple episodes of past experiences have to be remembered and creatively integrated in the context of the present to be successful. Starting from zero, where the robot knows nothing, we explore the computational basis of organization episodic memory in a cumulatively learning humanoid and address (1) how relevant past experiences can be reconstructed based on the present context, (2) how multiple stored episodic memories compete to survive in the neural space and not be forgotten, (3) how remembered past experiences can be combined with explorative actions to learn something new, and (4) how multiple remembered experiences can be recombined to generate novel behaviors (without exploration). Through the resulting behaviors of the robot as it builds, breaks, learns, and remembers, we emphasize that mechanisms of episodic memory are fundamental design features necessary to enable the survival of autonomous robots in a real world where neither everything can be known nor can everything be experienced.

show abstract

Inference Through Embodied Simulation in Cognitive Robots

Cited by 19 publications

References 59 publications

Towards a Brain-like Memory for Cognitive Robots. PhD Dissertation, University of Genova, Genova, Italy

Towards a Brain-like Memory for Cognitive Robots. PhD Dissertation, University of Genova, Genova, Italy

Humanoid infers Archimedes' principle: understanding physical relations and object affordances through cumulative learning experiences

A Neural Framework for Organization and Flexible Utilization of Episodic Memory in Cumulatively Learning Baby Humanoids

Contact Info

Product

Resources

About