arXiv subjects

Wolfgang Merkt

Publications and source records attributed to Wolfgang Merkt.

34 records · Page 2Linked to original sources

arXiv2021

Rapid Convex Optimization of Centroidal Dynamics using Block Coordinate Descent

In this paper we explore the use of block coordinate descent (BCD) to optimize the centroidal momentum dynamics for dynamically consistent multi-contact behaviors. The centroidal dynamics have recently received a large amount of attention in order to create physically realizable motions for robots with hands and feet while being computationally more tractable than full rigid body dynamics models. Our contribution lies in exploiting the structure of the dynamics in order to simplify the original non-convex problem into two convex subproblems. We iterate between these two subproblems for a set number of iterations or until a consensus is reached. We explore the properties of the proposed optimization method for the centroidal dynamics and verify in simulation that motions generated by our approach can be tracked by the quadruped Solo12. In addition, we compare our method to a recently proposed convexification using a sequence of convex relaxations as well as a more standard interior point method used in the off- the-shelf solver IPOPT to show that our approach finds similar, if not better, trajectories (in terms of cost), and is more than four times faster than both approaches. Finally, compared to previous approaches, we note its practicality due to the convex nature of each subproblem which allows our method to be used with any off-the-shelf quadratic programming solver.

cs.RO↗

arXiv2021

HapFIC: An Adaptive Force/Position Controller for Safe Environment Interaction in Articulated Systems

Haptic interaction is essential for the dynamic dexterity of animals, which seamlessly switch from an impedance to an admittance behaviour using the force feedback from their proprioception. However, this ability is extremely challenging to reproduce in robots, especially when dealing with complex interaction dynamics, distributed contacts, and contact switching. Current model-based controllers require accurate interaction modelling to account for contacts and stabilise the interaction. In this manuscript, we propose an adaptive force/position controller that exploits the fractal impedance controller's passivity and non-linearity to execute a finite search algorithm using the force feedback signal from the sensor at the end-effector. The method is computationally inexpensive, opening the possibility to deal with distributed contacts in the future. We evaluated the architecture in physics simulation and showed that the controller can robustly control the interaction with objects of different dynamics without violating the maximum allowable target forces or causing numerical instability even for very rigid objects. The proposed controller can also autonomously deal with contact switching and may find application in multiple fields such as legged locomotion, rehabilitation and assistive robotics.

cs.RO↗

arXiv2021

Residual Force Polytope: Admissible Task-Space Forces of Dynamic Trajectories

We propose a representation for the set of forces a robot can counteract using full system dynamics: the residual force polytope. Given the nominal torques required by a dynamic motion, this representation models the forces which can be sustained without interfering with that motion. The residual force polytope can be used to analyze and compare the set of admissible forces of different trajectories, but it can also be used to define metrics for solving optimization problems, such as in trajectory optimization or system design. We demonstrate how such a metric can be applied to trajectory optimization and compare it against other objective functions typically used. Our results show that the trajectories computed by optimizing objectives defined as functions of the residual force polytope are more robust to unknown external disturbances. The computational cost of these metrics is relatively high and not compatible with the short planning times required by online methods, but they are acceptable for planning motions offline.

cs.RO↗

arXiv2021

Memory Clustering using Persistent Homology for Multimodality- and Discontinuity-Sensitive Learning of Optimal Control Warm-starts

Shooting methods are an efficient approach to solving nonlinear optimal control problems. As they use local optimization, they exhibit favorable convergence when initialized with a good warm-start but may not converge at all if provided with a poor initial guess. Recent work has focused on providing an initial guess from a learned model trained on samples generated during an offline exploration of the problem space. However, in practice the solutions contain discontinuities introduced by system dynamics or the environment. Additionally, in many cases multiple equally suitable, i.e., multi-modal, solutions exist to solve a problem. Classic learning approaches smooth across the boundary of these discontinuities and thus generalize poorly. In this work, we apply tools from algebraic topology to extract information on the underlying structure of the solution space. In particular, we introduce a method based on persistent homology to automatically cluster the dataset of precomputed solutions to obtain different candidate initial guesses. We then train a Mixture-of-Experts within each cluster to predict state and control trajectories to warm-start the optimal control solver and provide a comparison with modality-agnostic learning. We demonstrate our method on a cart-pole toy problem and a quadrotor avoiding obstacles, and show that clustering samples based on inherent structure improves the warm-start quality.

cs.RO↗

arXiv2021

Sparsity-Inducing Optimal Control via Differential Dynamic Programming

Optimal control is a popular approach to synthesize highly dynamic motion. Commonly, $L_2$ regularization is used on the control inputs in order to minimize energy used and to ensure smoothness of the control inputs. However, for some systems, such as satellites, the control needs to be applied in sparse bursts due to how the propulsion system operates. In this paper, we study approaches to induce sparsity in optimal control solutions -- namely via smooth $L_1$ and Huber regularization penalties. We apply these loss terms to state-of-the-art DDP-based solvers to create a family of sparsity-inducing optimal control methods. We analyze and compare the effect of the different losses on inducing sparsity, their numerical conditioning, their impact on convergence, and discuss hyperparameter settings. We demonstrate our method in simulation and hardware experiments on canonical dynamics systems, control of satellites, and the NASA Valkyrie humanoid robot. We provide an implementation of our method and all examples for reproducibility on GitHub.

cs.RO↗

arXiv2021

Predicted Composite Signed-Distance Fields for Real-Time Motion Planning in Dynamic Environments

We present a novel framework for motion planning in dynamic environments that accounts for the predicted trajectories of moving objects in the scene. We explore the use of composite signed-distance fields in motion planning and detail how they can be used to generate signed-distance fields (SDFs) in real-time to incorporate predicted obstacle motions. We benchmark our approach of using composite SDFs against performing exact SDF calculations on the workspace occupancy grid. Our proposed technique generates predictions substantially faster and typically exhibits an 81--97% reduction in time for subsequent predictions. We integrate our framework with GPMP2 to demonstrate a full implementation of our approach in real-time, enabling a 7-DoF Panda arm to smoothly avoid a moving robot.

cs.RO↗

arXiv2021

Inverse Dynamics vs. Forward Dynamics in Direct Transcription Formulations for Trajectory Optimization

Benchmarks of state-of-the-art rigid-body dynamics libraries report better performance solving the inverse dynamics problem than the forward alternative. Those benchmarks encouraged us to question whether that computational advantage would translate to direct transcription, where calculating rigid-body dynamics and their derivatives accounts for a significant share of computation time. In this work, we implement an optimization framework where both approaches for enforcing the system dynamics are available. We evaluate the performance of each approach for systems of varying complexity, for domains with rigid contacts. Our tests reveal that formulations using inverse dynamics converge faster, require less iterations, and are more robust to coarse problem discretization. These results indicate that inverse dynamics should be preferred to enforce the nonlinear system dynamics in simultaneous methods, such as direct transcription.

cs.RO↗

arXiv2021

CPG-ACTOR: Reinforcement Learning for Central Pattern Generators

Central Pattern Generators (CPGs) have several properties desirable for locomotion: they generate smooth trajectories, are robust to perturbations and are simple to implement. Although conceptually promising, we argue that the full potential of CPGs has so far been limited by insufficient sensory-feedback information. This paper proposes a new methodology that allows tuning CPG controllers through gradient-based optimization in a Reinforcement Learning (RL) setting. To the best of our knowledge, this is the first time CPGs have been trained in conjunction with a MultilayerPerceptron (MLP) network in a Deep-RL context. In particular, we show how CPGs can directly be integrated as the Actor in an Actor-Critic formulation. Additionally, we demonstrate how this change permits us to integrate highly non-linear feedback directly from sensory perception to reshape the oscillators' dynamics. Our results on a locomotion task using a single-leg hopper demonstrate that explicitly using the CPG as the Actor rather than as part of the environment results in a significant increase in the reward gained over time (6x more) compared with previous approaches. Furthermore, we show that our method without feedback reproduces results similar to prior work with feedback. Finally, we demonstrate how our closed-loop CPG progressively improves the hopping behaviour for longer training epochs relying only on basic reward functions.

cs.RO↗

arXiv2020

Safe and Compliant Control of Redundant Robots Using Superimposition of Passive Task-Space Controllers

Safe and compliant control of dynamic systems in interaction with the environment, e.g., in shared workspaces, continues to represent a major challenge. Mismatches in the dynamic model of the robots, numerical singularities, and the intrinsic environmental unpredictability are all contributing factors. Online optimization of impedance controllers has recently shown great promise in addressing this challenge, however, their performance is not sufficiently robust to be deployed in challenging environments. This work proposes a compliant control method for redundant manipulators based on a superimposition of multiple passive task-space controllers in a hierarchy. Our control framework of passive controllers is inherently stable, numerically well-conditioned (as no matrix inversions are required), and computationally inexpensive (as no optimization is used). We leverage and introduce a novel stiffness profile for a recently proposed passive controller with smooth transitions between the divergence and convergence phases making it particularly suitable when multiple passive controllers are combined through superimposition. Our experimental results demonstrate that the proposed method achieves sub-centimeter tracking performance during demanding dynamic tasks with fast-changing references, while remaining safe to interact with and robust to singularities. he proposed framework achieves such results without knowledge of the robot dynamics and thanks to its passivity is intrinsically stable. The data further show that the robot can fully take advantage of the redundancy to maintain the primary task accuracy while compensating for unknown environmental interactions, which is not possible from current frameworks that require accurate contact information.

cs.RO↗

arXiv2020

Optimizing Dynamic Trajectories for Robustness to Disturbances Using Polytopic Projections

This paper focuses on robustness to disturbance forces and uncertain payloads. We present a novel formulation to optimize the robustness of dynamic trajectories. A straightforward transcription of this formulation into a nonlinear programming problem is not tractable for state-of-the-art solvers, but it is possible to overcome this complication by exploiting the structure induced by the kinematics of the robot. The non-trivial transcription proposed allows trajectory optimization frameworks to converge to highly robust dynamic solutions. We demonstrate the results of our approach using a quadruped robot equipped with a manipulator.

cs.RO↗

arXiv2020

Modeling and Control of a Hybrid Wheeled Jumping Robot

In this paper, we study a wheeled robot with a prismatic extension joint. This allows the robot to build up momentum to perform jumps over obstacles and to swing up to the upright position after the loss of balance. We propose a template model for the class of such two-wheeled jumping robots. This model can be considered as the simplest wheeled-legged system. We provide an analytical derivation of the system dynamics which we use inside a model predictive controller (MPC). We study the behavior of the model and demonstrate highly dynamic motions such as swing-up and jumping. Furthermore, these motions are discovered through optimization from first principles. We evaluate the controller on a variety of tasks and uneven terrains in a simulator.

cs.RO↗

arXiv2020

Bio-mimetic Adaptive Force/Position Control Using Fractal Impedance

The ability of animals to interact with complex dynamics is unmatched in robots. Especially important to the interaction performances is the online adaptation of body dynamics, which can be modeled as an impedance behaviour. However, the variable impedance controller still possesses a challenge in the current control frameworks due to the difficulties of retaining stability when adapting the controller gains. The fractal impedance controller has been recently proposed to solve this issue. However, it still has limitations such as sudden jumps in force when it starts to converge to the desired position and the lack of a force feedback loop. In this manuscript, two improvements are made to the control framework to solve these limitations. The force discontinuity has been addressed introducing a modulation of the impedance via a virtual antagonist that modulates the output force. The force tracking has been modeled after the parallel force/position controller architecture. In contrast to traditional methods, the fractal impedance controller enables the implementation of a search algorithm on the force feedback to adapt its behaviour on the external environment instead of on relying on \textit{a priori} knowledge of the external dynamics. Preliminary simulation results presented in this paper show the feasibility of the proposed approach, and it allows to evaluate the trade-off that needs to be made when relying on the proposed controller for interaction. In conclusion, the proposed method mimics the behaviour of an agonist/antagonist system adapting to unknown external dynamics, and it may find application in computational neuroscience, haptics, and interaction control.

cs.RO↗

arXiv2020

Crocoddyl: An Efficient and Versatile Framework for Multi-Contact Optimal Control

We introduce Crocoddyl (Contact RObot COntrol by Differential DYnamic Library), an open-source framework tailored for efficient multi-contact optimal control. Crocoddyl efficiently computes the state trajectory and the control policy for a given predefined sequence of contacts. Its efficiency is due to the use of sparse analytical derivatives, exploitation of the problem structure, and data sharing. It employs differential geometry to properly describe the state of any geometrical system, e.g. floating-base systems. Additionally, we propose a novel optimal control algorithm called Feasibility-driven Differential Dynamic Programming (FDDP). Our method does not add extra decision variables which often increases the computation time per iteration due to factorization. FDDP shows a greater globalization strategy compared to classical Differential Dynamic Programming (DDP) algorithms. Concretely, we propose two modifications to the classical DDP algorithm. First, the backward pass accepts infeasible state-control trajectories. Second, the rollout keeps the gaps open during the early "exploratory" iterations (as expected in multiple-shooting methods with only equality constraints). We showcase the performance of our framework using different tasks. With our method, we can compute highly-dynamic maneuvers (e.g. jumping, front-flip) within few milliseconds.

cs.RO↗

arXiv2020

Learning Whole-body Motor Skills for Humanoids

This paper presents a hierarchical framework for Deep Reinforcement Learning that acquires motor skills for a variety of push recovery and balancing behaviors, i.e., ankle, hip, foot tilting, and stepping strategies. The policy is trained in a physics simulator with realistic setting of robot model and low-level impedance control that are easy to transfer the learned skills to real robots. The advantage over traditional methods is the integration of high-level planner and feedback control all in one single coherent policy network, which is generic for learning versatile balancing and recovery motions against unknown perturbations at arbitrary locations (e.g., legs, torso). Furthermore, the proposed framework allows the policy to be learned quickly by many state-of-the-art learning algorithms. By comparing our learned results to studies of preprogrammed, special-purpose controllers in the literature, self-learned skills are comparable in terms of disturbance rejection but with additional advantages of producing a wide range of adaptive, versatile and robust behaviors.

cs.RO↗

arXiv2019

Comparing Alternate Modes of Teleoperation for Constrained Tasks

Teleoperation of heavy machinery in industry often requires operators to be in close proximity to the plant and issue commands on a per-actuator level using joystick input devices. However, this is non-intuitive and makes achieving desired job properties a challenging task requiring operators to complete extensive and costly training. Despite this, operator fatigue is common with implications for personal safety, project timeliness, cost, and quality. While full automation is not yet achievable due to unpredictability and the dynamic nature of the environment and task, shared control paradigms allow operators to issue high-level commands in an intuitive, task-informed control space while having the robot optimize for achieving desired job properties. In this paper, we compare a number of modes of teleoperation, exploring both the number of dimensions of the control input as well as the most intuitive control spaces. Our experimental evaluations of the performance metrics were based on quantifying the difficulty of tasks based on the well known Fitts' law as well as a measure of how well constraints affecting the task performance were met. Our experiments show that higher performance is achieved when humans submit commands in low-dimensional task spaces as opposed to joint space manipulations.

cs.RO↗

arXiv2016

Scaling Sampling-based Motion Planning to Humanoid Robots

Planning balanced and collision-free motion for humanoid robots is non-trivial, especially when they are operated in complex environments, such as reaching targets behind obstacles or through narrow passages. We propose a method that allows us to apply existing sampling--based algorithms to plan trajectories for humanoids by utilizing a customized state space representation, biased sampling strategies, and a steering function based on a robust inverse kinematics solver. Our approach requires no prior offline computation, thus one can easily transfer the work to new robot platforms. We tested the proposed method solving practical reaching tasks on a 38 degrees-of-freedom humanoid robot, NASA Valkyrie, showing that our method is able to generate valid motion plans that can be executed on advanced full-size humanoid robots. We also present a benchmark between different motion planning algorithms evaluated on a variety of reaching motion problems. This allows us to find suitable algorithms for solving humanoid motion planning problems, and to identify the limitations of these algorithms.

cs.RO↗