Saved in:
Bibliographic Details
Main Authors: Wang, Runcong, Wang, Fengyi, Cheng, Gordon
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.07032
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911306662019072
author Wang, Runcong
Wang, Fengyi
Cheng, Gordon
author_facet Wang, Runcong
Wang, Fengyi
Cheng, Gordon
contents This paper presents a hetero-associative sequential memory system for mobile manipulators that learns compact, neuromorphic bindings between robot joint states and tactile observations to produce step-wise action decisions with low compute and memory cost. The method encodes joint angles via population place coding and converts skin-measured forces into spike-rate features using an Izhikevich neuron model; both signals are transformed into bipolar binary vectors and bound element-wise to create associations stored in a large-capacity sequential memory. To improve separability in binary space and inject geometry from touch, we introduce 3D rotary positional embeddings that rotate subspaces as a function of sensed force direction, enabling fuzzy retrieval through a softmax weighted recall over temporally shifted action patterns. On a Toyota Human Support Robot covered by robot skin, the hetero-associative sequential memory system realizes a pseudocompliance controller that moves the link under touch in the direction and with speed correlating to the amplitude of applied force, and it retrieves multi-joint grasp sequences by continuing tactile input. The system sets up quickly, trains from synchronized streams of states and observations, and exhibits a degree of generalization while remaining economical. Results demonstrate single-joint and full-arm behaviors executed via associative recall, and suggest extensions to imitation learning, motion planning, and multi-modal integration.
format Preprint
id arxiv_https___arxiv_org_abs_2512_07032
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Hetero-Associative Sequential Memory Model Utilizing Neuromorphic Signals: Validated on a Mobile Manipulator
Wang, Runcong
Wang, Fengyi
Cheng, Gordon
Robotics
This paper presents a hetero-associative sequential memory system for mobile manipulators that learns compact, neuromorphic bindings between robot joint states and tactile observations to produce step-wise action decisions with low compute and memory cost. The method encodes joint angles via population place coding and converts skin-measured forces into spike-rate features using an Izhikevich neuron model; both signals are transformed into bipolar binary vectors and bound element-wise to create associations stored in a large-capacity sequential memory. To improve separability in binary space and inject geometry from touch, we introduce 3D rotary positional embeddings that rotate subspaces as a function of sensed force direction, enabling fuzzy retrieval through a softmax weighted recall over temporally shifted action patterns. On a Toyota Human Support Robot covered by robot skin, the hetero-associative sequential memory system realizes a pseudocompliance controller that moves the link under touch in the direction and with speed correlating to the amplitude of applied force, and it retrieves multi-joint grasp sequences by continuing tactile input. The system sets up quickly, trains from synchronized streams of states and observations, and exhibits a degree of generalization while remaining economical. Results demonstrate single-joint and full-arm behaviors executed via associative recall, and suggest extensions to imitation learning, motion planning, and multi-modal integration.
title A Hetero-Associative Sequential Memory Model Utilizing Neuromorphic Signals: Validated on a Mobile Manipulator
topic Robotics
url https://arxiv.org/abs/2512.07032