Papers accepted at IROS 2023

Two papers accepted at the International Conference on Intelligent Robots and Systems (IROS) 2023, being held in Detroit.


Carlos Mastalli, Saroj Prasad Chhatoi, Thomas Corbères, Steve Tonneau and Sethu Vijayakumar,  Inverse-Dynamics MPC via Nullspace Resolution, IEEE Transactions on Robotics (T-RO), vol. 39(4), pp. 3222-3241 (2023). (Presented at: IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS 2023), Detroit, USA) [DOI] [video] [citation]

Optimal control (OC) using inverse dynamics provides numerical benefits, such as coarse optimization, cheaper computation of derivatives, and a high convergence rate. However, to take advantage of these benefits in model predictive control (MPC) for legged robots, it is crucial to handle efficiently its large number of equality constraints. To accomplish this, we first propose a novel approach to handle equality constraints based on nullspace parameterization. Our approach balances optimality, and both dynamics and equality-constraint feasibility appropriately, which increases the basin of attraction to high-quality local minima. To do so, we modify our feasibility-driven search by incorporating a merit function. Furthermore, we introduce a condensed formulation of inverse dynamics that considers arbitrary actuator models. We also propose a novel MPC based on inverse dynamics within a perceptive locomotion framework. Finally, we present a theoretical comparison of OC with forward and inverse dynamics and evaluate both numerically. Our approach enables the first application of inverse-dynamics MPC on hardware, resulting in the state-of-the-art dynamic climbing on the ANYmal robot. We benchmark it over a wide range of robotics problems and generate agile and complex maneuvers. We show the computational reduction of our nullspace resolution and condensed formulation (up to 47.3% ). We provide evidence of the benefits of our approach by solving coarse optimization problems with a high convergence rate (up to 10 Hz of discretization). Our algorithm is publicly available inside Crocoddyl.


Juan Del Aguila Ferrandis, Joao Moura and Sethu Vijayakumar, Nonprehensile Planar Manipulation through Reinforcement Learning with Multimodal Categorical Exploration, Proc. IEEE/RSJ Intl. Conf. on Intelligent Robots and Systems (IROS 2023), Detroit, USA (2023). [pdf] [video] [citation]

Developing robot controllers capable of achieving dexterous nonprehensile manipulation, such as pushing an object on a table, is challenging. The underactuated and hybrid-dynamics nature of the problem, further complicated by the uncertainty resulting from the frictional interactions, requires sophisticated control behaviors. Reinforcement Learning (RL) is a powerful framework for developing such robot controllers. However, previous RL literature addressing the nonprehensile pushing task achieves low accuracy, non-smooth trajectories, and only simple motions, i.e. without rotation of the manipulated object. We conjecture that previously used unimodal exploration strategies fail to capture the inherent hybrid-dynamics of the task, arising from the different possible contact interaction modes between the robot and the object, such as sticking, sliding, and separation. In this work, we propose a multimodal exploration approach through categorical distributions, which enables us to train planar pushing RL policies for arbitrary starting and target object poses, i.e. positions and orientations, and with improved accuracy. We show that the learned policies are robust to external disturbances and observation noise, and scale to tasks with multiple pushers. Furthermore, we validate the transferability of the learned policies, trained entirely in simulation, to a physical robot hardware using the KUKA iiwa robot arm. See our supplemental video:


IROS 2023