Multi-Cable Rolling Locomotion with Spherical Tensegrities Using Model Predictive Control and Deep Learning

Cera, Brian; Agogino, Alice M.

doi:10.1109/iros.2018.8594401

Cited by 16 publications

(8 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, as shown in Figure 3A , a straight three-link tensegrity prism is notable for its design simplicity but not well-suited for rolling locomotion due to high discontinuity. In order to enhance rolling smoothness while optimizing structural complexity, the six-link icosahedron ( Figure 3B ) is frequently selected to achieve rolling locomotion (Shibata et al, 2009 ; Khazanov et al, 2013 ; Bruce et al, 2014 ; Kim et al, 2014 ; Lin et al, 2016 ; Cera and Agogino, 2018 ; Vespignani et al, 2018 ). This morphology enables planar locomotion, but motion is characterized by discontinuous “tip-over” impacts between triangular faces.…”

Section: Locomotion and Tensegrity Robotsmentioning

confidence: 99%

“…This is due to the complexity of geometric morphologies that are challenging to visualize and requirement of prestress in the cables. Currently, the design methodologies utilize jigs, multiple sets of hands and precise fabrication to achieve symmetric cable tension and link compression (Böhm et al, 2016 ; Chen et al, 2017a ; Kim et al, 2017 ; Cera and Agogino, 2018 ). Recently, planar-to-three-dimensional solutions have been explored using flexible lattice networks which are excellent for fabricating known morphologies which may not be altered post-assembly (Chen et al, 2017a ; Zappetti et al, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

“…The compressive elements (links) are made of rigid material, including wood (Kim et al, 2014 ), plastics (Böhm et al, 2016 ), and metals (Paul et al, 2006 ; Sabelhaus et al, 2015 ; Chen et al, 2017a ; Kim et al, 2017 ). The tensile and compliant elements are fabricated using cables, metal extension springs (Böhm et al, 2012 ; Khazanov et al, 2013 ; Bruce et al, 2014 ; Lin et al, 2016 ; Kim et al, 2017 ; Cera and Agogino, 2018 ) and elastic cables comprised of various plastics (Paul et al, 2006 ; Chen et al, 2017a ; Zappetti et al, 2017 ; Mintchev et al, 2018 ). Springs may span the full cable length (Böhm et al, 2012 ; Khazanov et al, 2013 ), or pair in series with other cable materials (Bruce et al, 2014 ; Kim et al, 2017 ; Cera and Agogino, 2018 ).…”

Section: Introductionmentioning

confidence: 99%

“…Integration of these elements varies considerably, with some methods including hooks (Khazanov et al, 2013 ; Sabelhaus et al, 2015 ; Cera and Agogino, 2018 ), knots (Kim et al, 2014 ), and even clamps (Chen et al, 2017a ). Here, precision in fabrication and integration of component lengths is critical to achieve the desired balance of forces required by the mechanism.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Compact Shape Morphing Tensegrity Robots Capable of Locomotion

2019

View full text Add to dashboard Cite

Robustness, compactness, and portability of tensegrity robots make them suitable candidates for locomotion on unknown terrains. Despite these advantages, challenges remain relating to ease of fabrication, shape morphing (packing-unpacking), and locomotion capabilities. The paper introduces a design methodology for fabricating tensegrity robots of varying morphologies with modular components. The design methodology utilizes perforated links, coplanar (2D) alignment of components and individual cable tensioning to achieve a 3D tensegrity structure. These techniques are utilized to fabricate prism (three-link) tensegrity structures, followed by tensegrity robots in icosahedron (six-link), and shpericon (curved two-link) formation. The methodology is used to explore different robot morphologies that attempt to minimize structural complexity (number of elements) while facilitating smooth locomotion (impact between robot and surface). Locomotion strategies for such robots involve altering the position of center-of-mass (referred to as internal mass shifting) to induce “tip-over.” As an example, a sphericon formation comprising of two orthogonally placed circular arcs with conincident center illustrates smooth locomotion along a line (one degree of freedom). The design of curved links of tensegrity mechanisms facilitates continuous change of the point of contact (along the curve) that results from the tip-over. This contrasts to the sudden and piece-wise continuous change for the case of robots with traditional straight links which generate impulse reaction forces during locomotion. The two resulting robots—the Icosahedron and the Sphericon Tensegrity Robots—display shape morphing (packing-unpacking) capabilities and achieve locomotion through internal mass-shifting. The presented static equilibrium analysis of sphericon with mass is the first step in the direction of dynamic locomotion control of these curved link robots.

show abstract

Section: Locomotion and Tensegrity Robotsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Compact Shape Morphing Tensegrity Robots Capable of Locomotion

2019

View full text Add to dashboard Cite

show abstract

“…Evolutionary methods have also been applied to produce smooth rolling of the 6-bar in discrete choices of directions on hilly terrain, provided with contact information (Iscen et al, 2014). Supervised deep learning has been used to train a contextual policy for directed rolling on flat ground, when provided with an extensive training set generated by model predictive control (Cera and Agogino, 2018).…”

Section: Introductionmentioning

confidence: 99%

Adaptive tensegrity locomotion: Controlling a compliant icosahedron with symmetry-reduced reinforcement learning

Surovik

Wang

Vespignani

et al. 2019

The International Journal of Robotics Research

View full text Add to dashboard Cite

Tensegrity robots, which are prototypical examples of hybrid soft–rigid robots, exhibit dynamical properties that provide ruggedness and adaptability. They also bring about, however, major challenges for locomotion control. Owing to high dimensionality and the complex evolution of contact states, data-driven approaches are appropriate for producing viable feedback policies for tensegrities. Guided policy search (GPS), a sample-efficient hybrid framework for optimization and reinforcement learning, has previously been applied to generate periodic, axis-constrained locomotion by an icosahedral tensegrity on flat ground. Varying environments and tasks, however, create a need for more adaptive and general locomotion control that actively utilizes an expanded space of robot states. This implies significantly higher needs in terms of sample data and setup effort. This work mitigates such requirements by proposing a new GPS -based reinforcement learning pipeline, which exploits the vehicle’s high degree of symmetry and appropriately learns contextual behaviors that are sustainable without periodicity. Newly achieved capabilities include axially unconstrained rolling, rough terrain traversal, and rough incline ascent. These tasks are evaluated for a small variety of key model parameters in simulation and tested on the NASA hardware prototype, SUPERball. Results confirm the utility of symmetry exploitation and the adaptability of the vehicle. They also shed light on numerous strengths and limitations of the GPS framework for policy design and transfer to real hybrid soft–rigid robots.

show abstract