Search papers, labs, and topics across Lattice.
This paper introduces Simultaneous Contact Selection and Planning (SCSP), a cascaded optimization framework for contact-rich manipulation that addresses the challenge of autonomously generating contact location sequences. SCSP decouples the problem into Contact Selection Optimization (CSO), which uses a surrogate contact model for efficient global searching of optimal contact locations, and Contact Planning Optimization (CPO), which generates manipulation trajectories based on CSO's guidance. The framework demonstrates robust control and diverse manipulation behaviors in both simulations and real-world experiments, even with inaccurate dynamics and perceptual noise.
Robots can now autonomously figure out where to make contact for complex manipulations, opening the door to more versatile and robust automation.
We propose an optimization-based framework for robust contact-rich manipulation. Recent contact-implicit methods enable online hybrid planning across contact modes, allowing closed-loop manipulation for a given target state and contact location sequence of the robot and object. However, most existing approaches lack the ability to autonomously reason and generate diverse contact location sequences and manipulation trajectories, i.e., active contact location selection, which limits their applicability to relatively simple tasks. Active contact location selection is challenging due to complementarity in contact dynamics and the sparse gradients, making the design of a unified framework for contact selection and planning difficult. To address these challenges, we introduce Simultaneous Contact Selection and Planning (SCSP), a cascaded optimization framework comprising Contact Selection Optimization (CSO) and Contact Planning Optimization (CPO). CSO leverages a surrogate contact model and discrete-continuous optimization to efficiently resolve the nonsmoothness and coupling in contact selection, enabling online global searching of optimal contact locations. CPO performs prior-guided contact planning by evaluating the reference contact locations produced by CSO and generating corresponding manipulation trajectories in real time for redundant manipulators. Extensive simulations and real-world experiments demonstrate that SCSP produces diverse manipulation behaviors and robust control under inaccurate dynamics and perceptual noise. We further validate the generalization of the framework on challenging manipulation tasks. Project website: \href{https://sites.google.com/view/scsp-robot}{https://sites.google.com/view/scsp-robot}.