Brain-Based Robots A Means to Creating More Intelligent Machines - PowerPoint PPT Presentation

Brain-Based Robots A Means to Creating More Intelligent Machines Jeff Krichmar Cognitive Anteater Robotics Laboratory (CARL) Department of Cognitive Sciences Department of Computer Science 1

3 Who is Better at Recognizing Objects?

4 Who is Better at Cooperating?

5 Which can Distinguish Self from non-Self?

6 Who can Fly Better?

7 All These Intelligent Creatures Have Brains Species' Neurons' Synapses' Nematode( 302( 10 3( ( Fruit(Fly( 100,000( 10 7( ( Honeybee( 960,000( 10 9( ( ( Mouse( 75,000,000( 10 11( ( Cat( 1,000,000,000( 10 13( ( ( Human( 85,000,000,000( 10 15( ( ( Source(–(hCp://en.wikipedia.org/wiki/List_of_animals_by_number_of_neurons(

8

9

10

11

12 Properties of Neurons Action Potential & Synapse

13 Brain Computations • Massive parallelism (10 11 neurons) • Massive connectivity (10 15 synapses) • Excellent power-efficiency – ~ 20 W for 10 16 flops • Low-performance components (~100 Hz) • Low-speed comm. (~meters/sec) • Low-precision synaptic connections • Probabilistic responses and fault-tolerant • Autonomous learning

14

15 Brain Inspired Robots SyntheNc(methodology( • Developing a system that Understanding(through(building( demonstrates some level of cognitive ability can lead to a better understanding of cognition. • Building a robot or artifact that follows a cognitive model could lead to a system that demonstrates capabilities commonly found in the animal kingdom, but rarely found in artificial systems.

16

17 Design Principles for Neurorobots • Engage in a behavioral task. • Behavior controlled by a simulated nervous system that reflects the brain’s architecture and dynamics. • The world is an unlabelled place. – Organize the signals from the environment into categories without a priori knowledge or instruction. • A value system that signals the salience of environmental cues to the robot’s nervous system. • Needs to be situated in the real world. • Behavior and activity of its simulated nervous system must allow comparisons with empirical data. Krichmar,(J.L.,(and(Edelman,(G.M.((2005).( Ar#ficial)Life,) Vol.(11,(63W78.(

18 Morris Water Maze: A Test of Spatial Cognition Krichmar,(et(al.((2005)(( Proc(Natl(Acad(Sci )102 ,(2111W2116.( • Allows comparison of the robot’s behavior with biological cognition. • Need to demonstrate that cognitive robots can transition to the real world just as humans or animals do when they are outside a laboratory setting.

19( Cognitive robot that transitioned beyond the lab: The RatSLAM Project: Robot Spatial Navigation Wyeth,(Milford,(Schulz,(&(Wiles(in( Neuromorphic)and)Brain:Based)Robots,)CUP,)2011,)pp.)87:108. (

20 Morphological Computation and Cheap Design • The construction and design of agents that are built to exploit properties of the ecological niche will be much easier or “cheaper”. Pfeifer and Bongard, 2006.

21 Example of Morphological Computation -Passive Walkers • Cornell Ranger – Walked 40.5 miles without being recharged or touched by a person – The coordination of the walking was by the 6 onboard microprocessors. – Each step it falls and catches itself in a controlled manner. – Took 186,076 steps while only using 5 cents worth of electricity.

22 Example of Cheap Design Segway soccer ball capture mechanism Fleischer,(J.(G.,(et(al.(A(neurally(controlled(robot(competes(and(cooperates( with(humans(in(Segway(soccer.(ICRA(2006.(

23 Organisms Adapt Their Behavior Through Value Systems • Non-specific, modulatory signals to the rest of the brain. • Biases the outcome of synaptic efficacy in the direction needed to satisfy global needs. Vertebrate'Neuromodulatory'Systems' Serotonergic ( Noradrenergic ( Cholinergic ( Dopaminergic ( Edelman,(G.M.((1993).(Neural(Darwinism:(SelecNon(and(reentrant(signaling(in(higher(brain( funcNon.(Neuron )10 ,(115W125.(

24 Neuromodulation as a Robot Controller OrienNng(toward(a(posiNve(value(object(–(Dopaminergic(response( Cox(&(Krichmar,(IEEE(RoboNcs(&(AutomaNon(Magazine,(September(2009.((

25 Neuromodulation as a Robot Controller Withdrawing(from(a(negaNve(value(object(–(Serotonergic(response( Cox(&(Krichmar,(IEEE(RoboNcs(&(AutomaNon(Magazine,(September(2009.((

26 A Biologically Inspired Action Selection Algorithm Based on Principles of Neuromodulation • General-purpose control system that ties environmental events to a wide-range of values. • Adapts to novel and familiar environments by trading off between being anxious and curious. Krichmar, J.L. (2012) International Joint Conference on Neural Networks (IJCNN). Krichmar, J.L. (2013) Frontiers in Neurorobotics.

27 Case Study for Neurorobot Design Navigating a Cluttered Scene Using Vision Crossing a busy Walking through a crowd at intersection in Ethiopia the San Diego County Fair hCps://www.youtube.com/watch?v=UEIn8GJIg0E(

28 Visual Motion Pathway Dorsal Stream (Macaque) Spatial Localization and Action • Primary visual cortex (V1) – Tuned to simple attributes of shape, motion, color, texture, depth. • Middle temporal (MT) area – Tuned to coherent local motion (retinal flow) • Medial Superior Temporal (MST) area and Ventral Intra-Parietal (VIP) – Tuned to global, complex motion. – Self-motion and object motion. – Multimodal. (Britten,)2008))

29 V1 and MT Model 50 Hz LIP • Spatiotemporal-energy model of V1 0 Hz – Bank of linear space-time oriented filters (rate-based). spiking ... 50 Hz 0 Hz • Adapted from Simoncelli & Heeger, 1998. MT – Direction-selective cells. (eqn. 13) ... ... ... – Fully realized in CUDA. 50 Hz 0 Hz • Two-stage spiking model of MT (eqn. 12) – Izhikevich spiking neurons: regular- 50 Hz spiking / fast-spiking rate-based 0 Hz • 153,216 neurons. V1 • ~40 million synapses. 100 Hz • Runs in real-time with video. 0 Hz – Component Direction Selective cells. – Pattern Direction Selective cells: • Direction pooling + opponent Retina inhibition. • Signals the global pattern of motion. • Solves the aperture problem

30 Model Response to Motion Patterns Component and Pattern Selectivity Component6 Pa:ern6 direc7on6 direc7on6 selec7ve' selec7ve'

31 Visually Guided Robot Navigation Architecture and I/O ABR server Cortical model ABR client Image Obstacle component Le Carl RGB frames gray Goal component 320x240 30x80 (UDP) LGN 320x240px ~30fps V1 WiFi/3G MT goal Servo commands PPCl PPCr (TCP) Steering control ABR(=(Android(Based(Robot( hCp://www.socsci.uci.edu/~jkrichma/ABR(

32 Visually Guided Robot Navigation Server Control GUI and Results

33 Visually Guided Robot Navigation By a Spiking Neural Network of Visual Cortex

34 Comparison to Psychophysical Data • Dotted lines are human trajectories – Replicated with dynamical system by Fajen & Warren, 2003; 2007. – Comparable to neural simulation by Browning, Grossberg & Mingolla. • Colored lines are robot trajectories.

35 Visually Guided Robot Navigation • Demonstrated that large-scale cortical spiking neural network can: – Replicate neurophysiological and psychophysical findings. – Control autonomous robot in real time. • First step toward a complete embedded visual navigation system. – Simulated MT responses are sufficient for obstacle avoidance. • Brain based computing compatible with new neuromorphic hardware that is smaller, faster, and more efficient than conventional computers.

36

37 Open Issues • Most cognitive systems – Exist in sterile, highly controlled laboratory settings. – Rely too much on neural control driving the body and behavior instead of the other way around. • Failing to make systems that perform more than one function at a time.

38 Challenge Problem that Requires Full Suite of Cognitive Behaviors Disaster Relief, Search and Rescue

39 Search & Rescue with Smartphone Robots • Cognitive mapping • Navigation • Object recognition • Decision making • Cooperation

40 Team CARL Hirak( Kashyap( Tiffany( Hwu( Stas( Listopad( Back(row(from(lej(to(right:(Alexis(Craig,(Alex(Wang,(Michael(Beyeler,( Feng(Rong,(Timo(Oess,(Saideep(Gupta.( Front(row(from(lej(to(right:(Emily(Rounds,(Steve(Doubleday,(Jeffrey( Krichmar,(TingWShuo(Chou,(Nikil(DuC.((

41 The Brain is Embodied and the Body is Embedded in the Environment • Understanding how the brain’s mechanisms give rise to perception, cognition, emotion, action and social engagement will have a revolutionary impact on science, medicine, economic growth, security, and social wellbeing. • By developing neural models that follow the architecture and dynamics of brain networks, we can create a class of robots that operate more like humans and other biological organisms.

42 Thank You!! • More information can be found at: – http://www.socsci.uci.edu/~jkrichma