Recommended
More Related Content
Similar to Towards the targeted environment-specific evolution of robot components
Similar to Towards the targeted environment-specific evolution of robot components (20)
Recently uploaded
Recently uploaded (20)
Towards the targeted environment-specific evolution of robot components
- 1. Towards the Targeted Environment- Specific Evolution of Robot Components DATA61 Jack Collins1,2 PhD Student Dr. David Howard1 Research Scientist Frederic Maire2 Senior Lecturer Wade Geles1 Industrial Trainee 1 with Data61, Commonwealth Scientific and Industrial Research Organisation (CSIRO), Brisbane, Australia 2 with the Science and Engineering Faculty, Queensland University of Technology (QUT), Brisbane, Australia
- 2. • Design of robots typically involves: • Expert knowledge • Many man-hours • Product iterations • Influenced by human preconceptions • i.e. This shape performs well in this environment because … Motivation 2 |
- 3. • Ubiquity of Additive Manufacturing • Stereolithography (SLA) • Selective Laser Sintering (SLS) • Fused Deposition Modeling (3D Printing) • ect. • Growing assortment of construction materials • Thermoplastics (ABS, PLA, Nylon, ect.) • Metals (Steel, Stainless Steel, Titanium, Gold, Silver) • Glass • Ceramic Motivation 3 |
- 4. • Evolutionary Robotics – “Automated creation of autonomous robots inspired by Darwinian Evolution” • Brain and Body Co-evolved • Evolutionary Art • Our Approach – Mature Control Stack – Targeted Evolution – No Controller Evolution 4 | Karl Sims, 1994 Jeff Clune, 2013
- 5. 1: High Outline Design Space: 16x16X32 (8192) Voxels 5 | 0 = Empty 1 = Full A voxel
- 6. Project Chrono • Project Chrono: A high-fidelity physics simulator – Rigid Body – Flexible Body – Fluid Dynamics – Granular Terrain Modules for: • FEA • Parallel • Fluid-Solid Interaction • Irrlicht • OpenGL • Rendering • Python interface • Matlab Interface • Solidworks Plug-in http://projectchrono.org/ & http://sbel.wisc.edu/Animations/ 6 |
- 8. 1: High • Multiple Beziers with varying control points and thicknesses. Encoding (Representation) Bezier graphic from http://graphics.cs.ucdavis.edu/~joy/GeometricModelingLectures/Unit-4/Unit4.html 8 |
- 9. 1: High • Multiple Beziers with varying control points and thicknesses. Encoding (Representation) Bezier graphic from http://graphics.cs.ucdavis.edu/~joy/GeometricModelingLectures/Unit-4/Unit4.html 9 |
- 10. 1: High • Multiple Beziers with varying control points and thicknesses. Encoding (Representation) Bezier graphic from http://graphics.cs.ucdavis.edu/~joy/GeometricModelingLectures/Unit-4/Unit4.html 10 |
- 11. 1: High • Multiple Beziers with varying control points and thicknesses. Encoding (Representation) Bezier graphic from http://graphics.cs.ucdavis.edu/~joy/GeometricModelingLectures/Unit-4/Unit4.html 11 |
- 12. Fitness Function • Fitness of an individual is calculated using: – 𝜏: Accumulated Torque – 𝛿: Percentage of occupied voxels • A lower fitness is the objective 𝑓 = 𝜏 𝑛 𝑠𝑡𝑒𝑝𝑠 + 𝜏 𝑛 𝑠𝑡𝑒𝑝𝑠 × 𝛿 5 12 |
- 13. Genetic Algorithm • Combination of the parents and children. • Deletion of the worst performing half. • Elitism retains fittest parent. • Selection through tournament selection. • Crossover using a two-point crossover method, with the two crossover points randomly chosen values within the range of the shortest parents genotype. • Mutation – Gaussian distribution of each Bezier control point – Change Bezier thickness (20%) – Add/remove control point (20%) – Add/remove Bezier (10%) 13 |
- 14. Simulations 14 |
- 15. Experimental Setup • Population of 20 legs • Optimised for 100 generations • 30 experiments in total • 10 Experiments per environment – Soil - 7 Hours – Gravel – 2.7 Days – Fluid – 9.4 Days • Parallelised using OpenMP • Run on HPC • Across 600 cores • Not GPU enabled 15 |
- 16. Results 16 |
- 17. Results 17 |
- 18. Shared Voxels 18 | Correlation between: Avg. Percentage: Soil Soil 91.8% Soil Granite 74.1% Soil Fluid 54.4% Granite Granite 72.0% Granite Fluid 59.6% Fluid Fluid 67.5%
- 19. Environmental Comparison Legs Environ. Fluid Granite Soil Fluid 13.3767 8.6355 0.1537 Granite 58.5300 8.0856 0.1404 Soil 86.9735 117.0014 0.0904 19 |
- 20. Results Soil Leg Gravel Leg 20 |
- 22. Contributions & Future Work • High Fidelity Simulation • Representation • Easily Instantiable • Fully functioning & applicable • FEA (Finite Element Analysis) • Real-world Validation • Further representations • Evolving mind and body 22 |
- 24. CPPNs 24 |
Editor's Notes
- -Undergrad Work -QUT -CSIRO
- -Typically the design of robots requires … -And this is influenced by …
- The wide spread adoption of Additive Manufacturing Rapidly expanding assortment of construction materials
- -Evolutionary Robotics is -Early work by Jeff Clune -Evolutionary Art …. PicBreeder … EndlessForms -Our approach borrows from Evolutionary art in that we only evolve the morphology of robot components -Targeted evolution of components that face “ENVIRONMENTAL PRESSURES“ -This allows us to utilise the mature control stack
- -Design Space (Resolution) -Hypothesis –selected robot components—high fidelity simulation—high performance morphologies—environmental niche
- -American & Italy (Alessandra Tasoro) Irrlicht – 3D Engine
- -Trimesh (encoded with soil parameters-see white paper) -Particles = gravel -Particles = fluid
- -Bezier Spline – control points -direct encoding
- -3D Beziers -5-10 Beziers -3-8 control points -Length genotype
- -phenotype -STL -Spline thickness 1-3 -Meshlab processing
- -OBJ for Project Chrono -smooth -Decimate (10000 to less than 2000 faces) -Transform and Rotate
- -Two terms -Torque -Occupied Voxels -Remove redundant material -3D Printing
- Over 100 Days into 9.4 days
- -Soil legs being generally skinnier than the other two; as the leg cannot 'fall through' the soil, the second term in the fitness function has more influence on the final morphology. -Gravel legs having more bulk than soil legs, so as not to fall through the environment and require additional torque resulting from dragging a partially 'submerged' leg through the gravel. -Expect streamlined, thin design. -legs fall to the bottom of the environment container -large torque penalties regardless of morphology -local minima.
- Difficulty of environments: -Gravel converges in 20 generations, 8.7 to 8.1 -Fluid converges in 40 generations, 21.5 to 19.1 -Soil converges in 80 generations,
- -Soil mean of 425 -Gravel mean of 2071
- -Achieved a morphology similar to something human designed -multiple contact points in the environment -Redundant material -parts of splines that add useful structure or increase surface contact. -suggests an alternate representation may be preferred.