- RUB
- INI
- Research Groups
- Autonomous Robotics
Autonomous Robotics
Our research in autonomous robotics is aimed at demonstrating that neural dynamic architectures of embodied cognition can generate object-oriented actions and simple forms of cognition. We organize the work around a scenario in which a partially autonomous robot system interacts with human operators with whom they share a natural environment. The robot system must acquire scene understanding to interpret user commands and autonomously perform actions such as orienting toward objects, retrieving them, possibly manipulating them and handing them over to the human operator. Based on analogies with how nervous systems generate motor behavior and simple forms of cognition, we use attractor dynamics and their instabilities at three levels to generate movement trajectories, to generate goal-directed sequences of behaviors, and to derive task-relevant perceptual representations that support goal-directed behavior.
Interested in autonomous robotics?
Additional material, exercises, and software related to our research topics can be found on the external website related to our theoretical framework Dynamic Field Theory.
If you are a RUB student interested in our work, have a look at the lecture Autonomous Robotics: Action, Perception, and Cognition, or our lab course in autonomous robotics, found under "Teaching" on the left.
We also offer group study projects, as well as Bachelor, Master, and Diploma projects for students of various fields. Check the offered projects under "Teaching" or just contact our group leader with your needs and we will talk about possible projects.
If you would like to visit the lab, meet some of the people, and have a look at our robots, just send an email to our group leader.
For external students and researchers, we offer a yearly summer school on our methods, see the Dynamic Field Theory web pages for more information.
-
Neural Dynamic Principles for an Intentional Embodied Agent
-
Inverting a model of neuromuscular control to estimate descending activation patterns that generate fast-reaching movements
-
ROBOVERINE: A human-inspired neural robotic process model of active visual search and scene grammar in naturalistic environments
-
Visual selective attention: Priority is all you need
-
A Neural Process Model of Structure Mapping Accounts for Children’s Development of Analogical Mapping by Change in Inhibitory Control
-
Interaction of polarity and truth value - A neural dynamic architecture of negation processing
-
A Neural Dynamic Model Autonomously Drives a Robot to Perform Structured Sequences of Action Intentions
-
Neural dynamic foundations of a theory of higher cognition: the case of grounding nested phrases
-
The stabilization of visibility for sequentially presented, low-contrast objects: Experiments and neural field model
-
A Neural Dynamic Model Perceptually Grounds Nested Noun Phrases
-
Bridging DFT and DNNs: A neural dynamic process model of scene representation, guided visual search and scene grammar in natural scenes
-
A Perceptually Grounded Neural Dynamic Architecture Establishes Analogy Between Visual Object Pairs
-
A Neural Dynamic Model Perceptually Grounds Nested Noun Phrases
-
How do neural processes give rise to cognition? Simultaneously predicting brain and behavior with a dynamic model of visual working memory.
-
A neural dynamic process model of combined bottom-up and top-down guidance in triple conjunction visual search
-
A Neural Dynamic Model of the Perceptual Grounding of Spatial and Movement Relations
-
Motor Habituation: Theory and Experiment
-
Scene memory and spatial inhibition in visual search: A neural dynamic process model and new experimental evidence
-
Grounding Spatial Language in Perception by Combining Concepts in a Neural Dynamic Architecture
-
Computer mouse tracking reveals motor signatures in a cognitive task of spatial language grounding
-
A process account of the UnControlled Manifold uncontrolled manifold structure of joint space variance in pointing movements
-
The Dynamics of Neural Populations Capture the Laws of the Mind
-
Autonomous Sequence Generation for a Neural Dynamic Robot: Scene Perception, Serial Order, and Object-Oriented Movement
-
Neural dynamic concepts for intentional systems
-
Autonomously learning beliefs is facilitated by a neural dynamic network driving an intentional agent
-
A neural dynamic model for the perceptual grounding of spatial and movement relations
-
Sequences of discrete attentional shifts emerge from a neural dynamic architecture for conjunctive visual search that operates in continuous time
-
Anticipatory coarticulation in non-speeded arm movements can be motor-equivalent, carry-over coarticulation always is
-
Erste Ansätze zur automatischen Erkennung von Gruppenverhalten mithilfe des Computersehens
-
A Neural Dynamic Architecture That Autonomously Builds Mental Models
-
A Neural Dynamic Architecture for Reaching and Grasping Integrates Perception and Movement Generation and Enables On-Line Updating
-
Cue Integration by Similarity Rank List Coding — Application to Invariant Object Recognition
-
Mouse Tracking Shows Attraction to Alternative Targets While Grounding Spatial Relations
-
A Neural-Dynamic Architecture for Concurrent Estimation of Object Pose and Identity
-
A multi-joint model of quiet , upright stance accounts for the “uncontrolled manifold”-structure of joint variance
-
A neural dynamic model generates descriptions of object-oriented actions
-
Reaching for objects : a neural process account in a developmental perspective
-
Dynamic Neural Fields with Intrinsic Plasticity
-
Temporal Asymmetry in Dark–Bright Processing Initiates Propagating Activity across Primary Visual Cortex
-
Nonlinear dynamics in the perceptual grouping of connected surfaces
-
Developing Dynamic Field Theory Architectures for Embodied Cognitive Systems with cedar
-
Coordination of muscle torques stabilizes upright standing posture: an UCM analysis
-
Separating Timing, Movement Conditions and Individual Differences in the Analysis of Human Movement
-
A neural dynamic model parses object-oriented actions
-
A neural process model of learning to sequentially organize and activate pre-reaches
-
Carry-over coarticulation in joint angles
-
Parsing of action sequences: A neural dynamics approach
-
Learning the condition of satisfaction of an elementary behavior in dynamic field theory
-
Task-specific stability of abundant systems: Structure of variance and motor equivalence
-
Motor equivalence during multi-finger accurate force production
-
The Dynamics of Neural Activation Variables
-
Artificial Neural Networks — Methods and Applications in Bio-/Neuroinformatics
-
The Neural Dynamics of Goal-Directed Arm Movements: A Developmental Perspective
-
The Sequential Organization of Movement is Critical to the Development of Reaching: A Neural Dynamics Account
-
Learning to Look: a Dynamic Neural Fields Architecture for Gaze Shift Generation
-
A comparison between reactive potential fields and Attractor Dynamics
-
A neural dynamics architecture for grasping that integrates perception and movement generation and enables on-line updating
-
Reaching and grasping novel objects: Using neural dynamics to integrate and organize scene and object perception with movement generation
-
Neural Fields
-
Instance-based object recognition with simultaneous pose estimation using keypoint maps and neural dynamics
-
Reinforcement-Driven Shaping of Sequence Learning in Neural Dynamics
-
Change occurs when body meets environment: A review of the embodied nature of development
-
Contrasting accounts of direction and shape perception in short-range motion: Counterchange compared with motion energy detection.
-
A neural dynamics to organize timed movement : Demonstration in a robot ball bouncing task
-
Autonomous Neural Dynamics to Test Hypotheses in a Model of Spatial Language
-
A neural dynamic architecture resolves phrases about spatial relations in visual scenes
-
Neural-Dynamic Architecture for Looking: Shift from Visual to Motor Target Representation for Memory Saccade
-
Dynamic interactions between visual working memory and saccade target selection
-
Use of the Uncontrolled Manifold (UCM) Approach to Understand MotorVariability, Motor Equivalence, and Self-motion
-
Embodied Cognition, Neural Field Models of
-
Dynamical Systems Thinking: From Metaphor to Neural Theory
-
Coordination Dynamics
-
Correcting Pose Estimates during Tactile Exploration of Object Shape: a Neuro-robotic Study
-
Using Haptics to Extract Object Shape from Rotational Manipulations
-
Autonomous robot hitting task using dynamical system approach
-
Autonomous Reinforcement of Behavioral Sequences in Neural Dynamics
-
A software framework for cognition, embodiment, dynamics, and autonomy in robotics: cedar
-
Learning the Perceptual Conditions of Satisfaction of Elementary Behaviors
-
Dynamic Neural Fields as a Step Towards Cognitive Neuromorphic Architectures
-
Increasing Autonomy of Learning SensorimotorTransformations with Dynamic Neural Fields
-
Learning Sensorimotor Transformations with Dynamic Neural Fields
-
Using Dynamic Field Theory to Extend the Embodiment Stance toward Higher Cognition
-
Autonomous reinforcement of behavioral sequences in neural dynamics
-
Naturalistic arm movements during obstacle avoidance in 3D and the identification of movement primitives.
-
Neural Dynamics of Hierarchically Organized Sequences: a Robotic Implementation
-
A Dynamic Field Architecture for the Generation of Hierarchically Organized Sequences
-
Sensorimotor Learning Biases Choice Behavior: A Learning Neural Field Model for Decision Making
-
The Function and Fallibility of Visual Feature Integration: A Dynamic Neural Field Model of Illusory Conjunctions
-
A Neuro-Behavioral Model of Flexible Spatial Language Behaviors
-
Functional synergies underlying control of upright posture during changes in head orientation
-
A robotic architecture for action selection and behavioral organization inspired by human cognition
-
A neural mechanism for coordinate transformation predicts pre-saccadic remapping
-
How visual information links to multijoint coordination during quiet standing
-
A neural-dynamic architecture for flexible spatial language: intrinsic frames, the term “between”, and autonomy
-
The temporal dynamics of global-to-local feedback in the formation of hierarchical motion patterns: psychophysics and computational simulations.
-
Limb versus speech motor control: a conceptual review.
-
Autonomous movement generation for manipulators with multiple simultaneous constraints using the attractor dynamics approach
-
A neural-dynamic architecture for behavioral organization of an embodied agent
-
Motor equivalence and self-motion induced by different movement speeds
-
Dynamic Neural Fields as Building Blocks of a Cortex-Inspired Architecture for Robotic Scene Representation
-
Making a robotic scene representation accessible to feature and label queries
-
Motor Abundance Contributes to Resolving Multiple Kinematic Task Constraints
-
Measuring Perceptual Hysteresis with the Modified Method of Limits: Dynamics at the Threshold
-
Motor control theories and their applications
-
Natural human-robot interaction through spatial language: a dynamic neural fields approach
-
An embodied account of serial order: how instabilities drive sequence generation
-
Serial order in an acting system: a multidimensional dynamic neural fields implementation
-
Scene Representation for Anthropomorphic Robots: A Dynamic Neural Field Approach
-
Scenes and tracking with dynamic neural fields: How to update a robotic scene representation
-
A layered neural architecture for the consolidation, maintenance, and updating of representations in visual working memory.
-
A layered neural architecture for the consolidation, maintenance, and updating of representations in visual working memory.
-
A counterchange mechanism for the perception of motion.
-
Swing it to the Left, Swing it to the Right: Enacting Flexible Spatial Language Using a Neurodynamic Framework
-
An Integrative Framework for Spatial Language and Color: Robotic Demonstrations Using the Dynamic Field Theory.
-
Behaviorally Flexible Spatial Communication: Robotic Demonstrations of a Neurodynamic Framework
-
Redundancy, self-motion and motor control
-
Temporal stabilization of discrete movement in variable environments: an attractor dynamics approach
-
Dynamic Field Theory as a framework for understanding embodied cognition
-
Shorter latencies for motion trajectories than for flashes in population responses of cat primary visual cortex
-
Timing, Clocks, and Dynamical Systems
-
Target representation on an autonomous vehicle with low-level sensors
-
The distribution of neuronal population activation (DPA) as a tool to study interaction and integration in cortical representations
-
Parametric population representation of retinal location: Neuronal interaction dynamics in cat primary visual cortex
-
Using attractor dynamics to control autonomous vehicle motion
-
The dynamic approach to autonomous robotics demonstrated on a low-level vehicle platform
-
Population coding in cat visual cortex reveals nonlinear interactions as predicted by a neural field model
-
Dynamics of behavior: Theory and applications for autonomous robot architectures
-
A stochastic theory of phase transitions in human hand movement
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2004
2002
2000
1999
1998
1997
1996
1995
1986
-
A Neurodynamic Model for Haptic Spatiotemporal Integration
-
Cognitive object recognition based on dynamic field theory
-
A Neuro-Dynamic Architecture for Autonomous Visual Scene Representation
-
Autonomous generation and on-line updating of sequences of timed robotic actions: an attractor dynamics approach
-
Sequence generation in Dynamic Field Theory
-
Object recognition with dynamic neural fields
2017
2016
2015
2014
2010
2009
The Institut für Neuroinformatik (INI) is a interdisciplinary research unit of the Ruhr-Universität Bochum. We aim to understand fundamental principles that characterize how organisms generate behavior and cognition while linked to their environments through sensory and effector systems. Inspired by insights into natural cognitive systems, we seek new solutions to problems of information processing in artificial cognitive systems. We draw from a variety of disciplines that include experimental approaches from psychology and neurophysiology, theoretical approaches from physics, mathematics, and computer science, including, in particular, machine learning, artificial intelligence, autonomous robotics, and computer vision.
Universitätsstr. 150, Building NB, Room 3/32
D-44801 Bochum, Germany
Tel: (+49) 234 32-28967
Fax: (+49) 234 32-14210