Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userChainQueen: A Real-Time Differentiable Physical Simulator for Soft Robotics
104
0
0.0
(
0
)
Added by
Yuanming Hu
Publication date
2018
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Physical simulators have been widely used in robot planning and control. Among them, differentiable simulators are particularly favored, as they can be incorporated into gradient-based optimization algorithms that are efficient in solving inverse problems such as optimal control and motion planning. Simulating deformable objects is, however, more challenging compared to rigid body dynamics. The underlying physical laws of deformable objects are more complex, and the resulting systems have orders of magnitude more degrees of freedom and therefore they are significantly more computationally expensive to simulate. Computing gradients with respect to physical design or controller parameters is typically even more computationally challenging. In this paper, we propose a real-time, differentiable hybrid Lagrangian-Eulerian physical simulator for deformable objects, ChainQueen, based on the Moving Least Squares Material Point Method (MLS-MPM). MLS-MPM can simulate deformable objects including contact and can be seamlessly incorporated into inference, control and co-design systems. We demonstrate that our simulator achieves high precision in both forward simulation and backward gradient computation. We have successfully employed it in a diverse set of control tasks for soft robots, including problems with nearly 3,000 decision variables.
rate research
Read More
In this work we present a framework that is capable of accurately representing soft robotic actuators in a multiphysics environment in real-time. We propose a constraint-based dynamics model of a 1-dimensional pneumatic soft actuator that accounts for internal pressure forces, as well as the effect of actuator latency and damping under inflation and deflation and demonstrate its accuracy a full soft robotic snake with the composition of multiple 1D actuators. We verify our models accuracy in static deformation and dynamic locomotion open-loop control experiments. To achieve real-time performance we leverage the parallel computation power of GPUs to allow interactive control and feedback.
The current dominant paradigm for robotic manipulation involves two separate stages: manipulator design and control. Because the robots morphology and how it can be controlled are intimately linked, joint optimization of design and control can significantly improve performance. Existing methods for co-optimization are limited and fail to explore a rich space of designs. The primary reason is the trade-off between the complexity of designs that is necessary for contact-rich tasks against the practical constraints of manufacturing, optimization, contact handling, etc. We overcome several of these challenges by building an end-to-end differentiable framework for contact-aware robot design. The two key components of this framework are: a novel deformation-based parameterization that allows for the design of articulated rigid robots with arbitrary, complex geometry, and a differentiable rigid body simulator that can handle contact-rich scenarios and computes analytical gradients for a full spectrum of kinematic and dynamic parameters. On multiple manipulation tasks, our framework outperforms existing methods that either only optimize for control or for design using alternate representations or co-optimize using gradient-free methods.
Soft robotics is an emerging field of research where the robot body is composed of compliant and soft materials. It allows the body to bend, twist, and deform to move or to adapt its shape to the environment for grasping, all of which are difficult for traditional hard robots with rigid bodies. However, the theoretical basis and design principles for soft robotics are not well-founded despite their recognized importance. For example, the control of soft robots is outsourced to morphological attributes and natural processes; thus, the coupled relations between a robot and its environment are particularly crucial. In this paper, we propose a mathematical foundation for soft robotics based on category theory, which is a branch of abstract math where any notions can be described by objects and arrows. It allows for a rigorous description of the inherent characteristics of soft robots and their relation to the environment as well as the differences compared to conventional hard robots. We present a notion called the category of mobility that well describes the subject matter. The theory was applied to a model system and analysis to highlight the adaptation behavior observed in universal grippers, which are a typical example of soft robotics. This paper paves the way to developing a theoretical background and design principles for soft robotics.
We train embodied neural networks to plan and navigate unseen complex 3D environments, emphasising real-world deployment. Rather than requiring prior knowledge of the agent or environment, the planner learns to model the state transitions and rewards. To avoid the potentially hazardous trial-and-error of reinforcement learning, we focus on differentiable planners such as Value Iteration Networks (VIN), which are trained offline from safe expert demonstrations. Although they work well in small simulations, we address two major limitations that hinder their deployment. First, we observed that current differentiable planners struggle to plan long-term in environments with a high branching complexity. While they should ideally learn to assign low rewards to obstacles to avoid collisions, we posit that the constraints imposed on the network are not strong enough to guarantee the network to learn sufficiently large penalties for every possible collision. We thus impose a structural constraint on the value iteration, which explicitly learns to model any impossible actions. Secondly, we extend the model to work with a limited perspective camera under translation and rotation, which is crucial for real robot deployment. Many VIN-like planners assume a 360 degrees or overhead view without rotation. In contrast, our method uses a memory-efficient lattice map to aggregate CNN embeddings of partial observations, and models the rotational dynamics explicitly using a 3D state-space grid (translation and rotation). Our proposals significantly improve semantic navigation and exploration on several 2D and 3D environments, succeeding in settings that are otherwise challenging for this class of methods. As far as we know, we are the first to successfully perform differentiable planning on the difficult Active Vision Dataset, consisting of real images captured from a robot.
The Kilobot is a widely used platform for investigation of swarm robotics. Physical Kilobots are slow moving and require frequent recalibration and charging, which significantly slows down the development cycle. Simulators can speed up the process of testing, exploring and hypothesis generation, but usually require time consuming and error-prone translation of code between simulator and robot. Moreover, code of different nature often obfuscates direct comparison, as well as determination of the cause of deviation, between simulator and actual robot swarm behaviour. To tackle these issues we have developed a C-based simulator that allows those working with Kilobots to use the same programme code in both the simulator and the physical robots. Use of our simulator, coined Kilombo, significantly simplifies and speeds up development, given that a simulation of 1000 robots can be run at a speed 100 times faster than real time on a desktop computer, making high-throughput pre-screening possible of potential algorithms that could lead to desired emergent behaviour. We argue that this strategy, here specifically developed for Kilobots, is of general importance for effective robot swarm research. The source code is freely available under the MIT license.
suggested questions
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
