Grasping unknown objects in clutter remains challenging due to partial occlusions, self-occlusions, and frequent object interactions during execution. In this paper we present Grasp It Like a Pro 3.0 (GILP 3.0), a lightweight learning-from-demonstration pipeline for closed-loop clutter clearing with unknown objects. The method segments the scene from raw RGB-D point clouds, approximates candidate regions via MVBB decomposition, and predicts grasp pose and interaction wrench from compact MVBB descriptors using two histogram-based gradient-boosted decision-tree regressors trained from a limited number of human demonstrations. Grasp candidates are ranked with execution-oriented feasibility and collision-aware scoring, and the pipeline iteratively reacquires and replans after each attempt to handle object motion and occlusions in clutter. Real-robot experiments on a Franka Emika Panda with Franka Hand in 12 cluttered scenes (47 objects) achieve 95.7% perobject success and a 91.7% scene clearing rate, demonstrating a replicable and data-efficient solution for grasping unknown everyday objects in cluttered environments.

The robotics research community has developed several effective techniques for quadrupedal locomotion. Most of these methods ease the modeling and control problem by assuming a rigid contact between the feet and the terrain. However, in the case of compliant terrain or robots equipped with soft feet, this assumption no longer holds, as the contact point moves and the reaction forces experience a delay. This article presents a novel approach for quadrupedal locomotion in the presence of soft contacts. The control architecture consists of two blocks: 1) upstream, the motion planner (MP) computes a feasible trajectory using model predictive control (MPC) and 2) downstream, the tracking controller (TC) employs hierarchical optimization (HO) to achieve motion tracking. This choice allows the control architecture to employ a large time horizon without heavily compromising the model’s accuracy. For the first time, both blocks consider the contact compliance: in the MP, the classic linear inverted pendulum model is extended by proposing the soft bilinear inverted pendulum (SBIP) model; conversely, the TC is a whole-body controller (WBC) that considers the full dynamics model, including the soft contacts. Simulations with multiple quadrupedal robots demonstrate that the proposed approach enables traversing soft terrains with improved stability and efficiency. Furthermore, the performance benefits of including the compliance in the MP and TC are evaluated. Finally, experiments on the SOLO12 robot walking on soft terrain validate the proposed approach’s effectiveness.

One of the primary challenges in quadrupedal locomotion pertains to the robot’s ability to adapt its gait to the surrounding environment and the desired task. This capability allows quadrupedal robots to select suitable foothold locations and adjust their gait for optimal performance. We address the problem of gait adaptation using trajectory optimization (TO), which takes into account the simplified switched system’s dynamics and optimizes the different phases of motion in which we split the robot’s movement. The robot dynamic model is a single rigid body (SRB) with a rigid contact model and foot positions. We apply contact and friction cone constraints to ensure a physically feasible motion of the real robot. We tackle the optimization using the direct multiple shooting (DMS) method. Leveraging kinematic inversion to map the base and feet positions into joint positions, velocities, and accelerations, we design a controller that combines iterative learning control (ILC) and proportional derivative (PD) feedback control. The iterative controller compensates for the sim-to-real gap, allowing the real robot to learn the task during the execution of the latter. We evaluate the performance of the proposed approach on two different quadrupedal robots and on different terrains.

Mastering rough terrain locomotion is a tough challenge for robots due to its dynamic, unpredictable nature and frequent physical contact. Traditionally, robots rely on carefully planned foot placements to maintain grip and stability. Recent advancements in quadruped robot feet offer diverse shapes and high grip for various terrains. However, control systems and planners often struggle to leverage these varied capabilities, relying instead on simplified foot models e.g., ball-like, flat. The simplified feet models committed to the single shape of the foot can not be used on robots equipped with diverse feet or modern adaptive feet. This work proposes a novel foothold optimization method that efficiently searches for optimal contact points for different foot shapes using a polynomial approximation. The system leverages a Convolutional Neural Network (CNN) trained on simulated data to predict a cost for each candidate foothold. We show that a single neural network can work with different and new foot mechanical designs without retraining the system. We experimentally validate our system on the ANYmal robot using both ball feet and adaptive soft feet, in indoor and outdoor environments, finding that our system improves stability, in terms of pitch and roll angles of the base, with respect to a state-of-the-art method.

Soft robots are deformable, compliant, and underactuated systems. During any task, due to their enormous capability of body deformation, the relative degree may not be well-defined. Since the applicability of the large majority of the state-of-the-art control techniques depends on this property, they frequently encounter singularities. This fact can jeopardize the system’s safety, prevent the correct task execution, or reduce performance. In this work, we investigate the relative degree of dependence for a class of compliant underactuated arms. Our method leverages the well-known strong inertial coupling hypothesis that, if holds, guarantees a constant relative degree of two. We generalize it by introducing coupling conditions where the relative degree is assured to be piecewise constant and greater than two. Relying on the design parameters, we analyze the dynamic evolution of the coupling conditions, which are then used to synthesize a classic input-output feedback controller. We also prove the stability of the closed-loop system. Finally, we validate the efficacy of the approach in simulation and on real hardware using a two and three degrees of freedom underactuated compliant arms with varying stiffness profiles, tasks, and disturbances.

Performing precise, repetitive motions is essential in many robotic and automation systems. Iterative learning control (ILC) allows determining the necessary control command by using a very rough system model to speed up the process. Functional iterative learning control is a novel technique that promises to solve several limitations of classic ILC. It operates by merging the input space into a large functional space, resulting in an over-determined control task in the iteration domain. In this way, it can deal with systems having more outputs than inputs and accelerate the learning process without resorting to model discretizations. However, the framework lacks so far a validation in experiments. This paper aims to provide such experimental validation in the context of robotics. To this end, we designed and built a one-link flexible arm that is actuated by a stepper motor, which makes the development of an accurate model more challenging and the validation closer to the industrial practice. We provide multiple experimental results across several conditions, proving the feasibility of the method in practice.

Soft robots can execute tasks with safer interactions. However, control techniques that can effectively exploit the systems' capabilities are still missing. Differential dynamic programming (DDP) has emerged as a promising tool for achieving highly dynamic tasks. But most of the literature deals with applying the DDP to articulated soft robots by using numerical differentiation, in addition to using pure feed-forward control to perform explosive tasks. Further, underactuated compliant robots are known to be difficult to control and the use of DDP-based algorithms to control them is not yet addressed. We propose an efficient DDP-based algorithm for trajectory optimization of articulated soft robots that can optimize the state trajectory, input torques, and stiffness profile. We provide an efficient method to compute the forward dynamics and the analytical derivatives of series elastic actuators (SEA)/variable stiffness actuators (VSA) and underactuated compliant robots. We present a state-feedback controller that uses locally optimal feedback policies obtained from the DDP. We show through simulations and experiments that the use of feedback is crucial in improving the performance and stabilization properties of various tasks. We also show that the proposed method can be used to plan and control underactuated compliant robots with varying degrees of underactuation effectively.

With the improvements in their computational and physical intelligence, robots are now capable of operating in real-world environments. However, manipulation and grasping capabilities are still areas that require significant improvements. To address this, we introduce a new data-driven grasp planning algorithm called Grasp it Like a Pro 2.0. This algorithm utilizes a small number of human demonstrations to teach a robot how to grasp arbitrary objects. By decomposing objects into basic shapes, our algorithm generates candidate grasps that can generalize to different object's geometry. The algorithm selects the grasp to execute based on a selection policy that maximizes a novel grasp quality metric introduced in this article. This metric considers the complex interdependencies between the predicted grasp, the local approximation produced by the basic shape decomposition, and the gripper used. We evaluate our approach against multiple baselines using different grippers and objects. The results demonstrate the effectiveness of our method in generating and selecting high-quality and reliable grasps. With a soft underactuated robotic hand, our algorithm achieves a 94.0% success rate in 150 grasps across 30 different objects. Similarly, with a rigid gripper, it achieves an 85.0% success rate in 80 grasps across 16 different objects.

The attention given to impedance control in recent years does not match a similar focus on the choice of impedance values that the controller should execute. Current methods are hardly general and often compute fixed controller gains relying on the use of expensive sensors. In this article, we address the problem of online impedance planning for Cartesian impedance controllers that do not assign the closed-loop inertia. We propose an optimization-based algorithm that, given the Cartesian inertia, computes the stiffness and damping gains without relying on force/torque measurements and so that the effects of perturbations are less than a maximum acceptable value. By doing so, we increase robot resilience to unexpected external disturbances while guaranteeing performance and robustness. The algorithm provides an analytical solution in the case of impedance-controlled robots with diagonally dominant inertia matrix. Instead, established numerical methods are employed to deal with the more common case of nondiagonally dominant inertia. Our work attempts to create a general impedance planning framework, which needs no additional hardware and is easily applicable to any robotic system. Through experiments on real robots, including a quadruped and a robotic arm, our method is shown to be employable in real time and to lead to satisfactory behaviors.

Operations involving safe interactions in unstructured environments require robots with adapting behaviors. Compliant manipulators are a promising technology to achieve this goal. Despite that, some classical control problems such as following a trajectory are still open. A typical solution is to compensate the system dynamics with feedback loops. However, this solution increases the effective robot stiffness and jeopardizes the safety property provided by the compliant design. On the other hand, purely feedforward approaches can achieve good tracking performance while preserving the robot intrinsic compliance. However, a feedforward control framework for robots with passive elastic joints is still missing. This article presents an iterative learning control algorithm for purely feedforward trajectory tracking for compliant underactuated arms. Each arm is composed of active elastic joints and a generic number of passive ones connected through rigid links. We prove the convergence of the iterative method, also in the presence of uncertainties and bounded disturbances. Different output functions are analyzed providing conditions, based on the system inertial properties that ensure the algorithm applicability. Additionally, an automatic selection of the learning gain is proposed. Finally, we extensively validate the theoretical results with simulations and experiments.

Trajectory tracking of flexible link robots is a classical control problem. Historically, the link elasticity was considered as something to be removed. Hence, the control performance was guaranteed by adopting high-gain feedback loops and, possibly, a dynamic compensation with the result to stiffen up the dynamic behavior of the robot. Nowadays, robots are pushed more and more towards a safe physical interaction with a less and less structured environment. Hence, the design and control of the robots moved to an on-purpose introduction of highly compliant elements in the robot bodies, the so-called soft robotics, and towards control approaches that aim to provide the tracking performance without a substantial change in the robot dynamic behavior. Following this approach, we present an iterative learning control that relies mainly on a feedforward component, hence preserves the robot dynamics, for trajectory tracking of a one-link flexible arm. We provide a condition, based on the system dynamics and similar to the Strong Inertially Coupled property, that ensures the applicability of the proposed control method. Finally, we report simulation and experimental tests to validate the theoretical results.

Real world applications require robots to operate in unstructured environments. This kind of scenarios may lead to unexpected environmental contacts or undesired interactions, which may harm people or impair the robot. Adjusting the behavior of the system through impedance control techniques is an effective solution to these problems. However, selecting an adequate impedance is not a straightforward process. Normally, robot users manually tune the controller gains with trial and error methods. This approach is generally slow and requires practice. Moreover, complex tasks may require different impedance during different phases of the task. This paper introduces an optimization algorithm for online planning of the Cartesian robot impedance to adapt to changes in the task, robot configuration, expected disturbances, external environment and desired performance, without employing any direct force measurements. We provide an analytical solution leveraging the mass-spring-damper behavior that is conferred to the robot body by the Cartesian impedance controller. Stability during gains variation is also guaranteed. The effectiveness of the method is experimentally validated on the quadrupedal robot ANYmal. The variable impedance helps the robot to tackle challenging scenarios like walking on rough terrain and colliding with an obstacle.

Despite the classic nature of the problem, trajectory tracking for soft robots, i.e., robots with compliant elements deliberately introduced in their design, still presents several challenges. One of these is to design controllers which can obtain sufficiently high performance while preserving the physical characteristics intrinsic to soft robots. Indeed, classic control schemes using high-gain feedback actions fundamentally alter the natural compliance of soft robots effectively stiffening them, thus de facto defeating their main design purpose. As an alternative approach, we consider here using a low-gain feedback, while exploiting feedforward components. In order to cope with the complexity and uncertainty of the dynamics, we adopt a decentralized, iteratively learned feedforward action, combined with a locally optimal feedback control. The relative authority of the feedback and feedforward control actions adapts with the degree of uncertainty of the learned component. The effectiveness of the method is experimentally verified on several robotic structures and working conditions, including unexpected interactions with the environment, where preservation of softness is critical for safety and robustness.