Biomimetic and compliant robotic hands offer the potential for human-like dexterity, but controlling them is challenging due to high dimensionality, complex contact interactions, and uncertainties in state estimation. Sampling-based model predictive control (MPC), using a physics simulator as the dynamics model, is a promising approach for generating contact-rich behavior. However, sampling-based MPC has yet to be evaluated on physical (non-simulated) robotic hands, particularly on compliant hands with state uncertainties. We present the first successful demonstration of in-hand manipulation on a physical biomimetic tendon-driven robot hand using sampling-based MPC. While sampling-based MPC does not require lengthy training cycles like reinforcement learning approaches, it still necessitates adapting the task-specific objective function to ensure robust behavior execution on physical hardware. To adapt the objective function, we integrate a visual language model (VLM) with a real-time optimizer (MuJoCo MPC). We provide the VLM with a high-level human language description of the task, and a video of the hand's current behavior. The VLM iteratively adapts the objective function, enabling effective behavior generation. In our experiments, the hand achieves an average ball rolling speed of 0.35 rad/s, successful ball flips, and catching with a 67\% success rate. Our results demonstrate that sampling-based MPC is a promising approach for generating dexterous manipulation skills on biomimetic hands without extensive training cycles.

This paper addresses the "Teenager's Problem": efficiently removing scattered garments from a planar surface into a basket. As grasping and transporting individual garments is highly inefficient, we propose policies to select grasp locations for multiple garments using an overhead camera. Our core approach is segment-based, which uses segmentation on the overhead RGB image of the scene. We propose a Probabilistic Set Cover formulation of the problem, aiming to minimize the number of grasps that clear all garments off the surface. Grasp efficiency is measured by Objects per Transport (OpT), which denotes the average number of objects removed per trip to the laundry basket. Additionally, we explore several depth-based methods, which use overhead depth data to find efficient grasps. Experiments suggest that our segment-based method increases OpT by $50\%$ over a random baseline, whereas combined hybrid methods yield improvements of $33\%$. Finally, a method employing consolidation (with segmentation) is considered, which locally moves the garments on the work surface to increase OpT, when the distance to the basket is much greater than the local motion distances. This yields an improvement of $81\%$ over the baseline.

We propose a method to track the 6D pose of an object over time, while the object is under non-prehensile manipulation by a robot. At any given time during the manipulation of the object, we assume access to the robot joint controls and an image from a camera. We use the robot joint controls to perform a physics-based prediction of how the object might be moving. We then combine this prediction with the observation coming from the camera, to estimate the object pose as accurately as possible. We use a particle filtering approach to combine the control information with the visual information. We compare the proposed method with two baselines: (i) using only an image-based pose estimation system at each time-step, and (ii) a particle filter which does not perform the computationally expensive physics predictions, but assumes the object moves with constant velocity. Our results show that making physics-based predictions is worth the computational cost, resulting in more accurate tracking, and estimating object pose even when the object is not clearly visible to the camera.

We consider a decluttering problem where multiple rigid convex polygonal objects rest in randomly placed positions and orientations on a planar surface and must be efficiently transported to a packing box using both single and multi-object grasps. Prior work considered frictionless multi-object grasping. In this paper, we introduce friction to increase the number of potential grasps for a given group of objects, and thus increase picks per hour. We train a neural network using real examples to plan robust multi-object grasps. In physical experiments, we find a 13.7% increase in success rate, a 1.6x increase in picks per hour, and a 6.3x decrease in grasp planning time compared to prior work on multi-object grasping. Compared to single-object grasping, we find a 3.1x increase in picks per hour.

Abstract-- We present the "Busboy Problem": automating an efficient decluttering of cups, bowls, and silverware from a planar surface. As grasping and transporting individual items is highly inefficient, we propose policies to generate grasps for multiple items. We introduce the metric of Objects per Trip (OpT) carried by the robot to the collection bin to analyze the improvement seen as a result of our policies. In physical experiments with singulated items, we find that consolidation and multi-object grasps resulted in an 1.8x improvement in OpT, compared to methods without multi-object grasps. See https://sites.google.com/berkeley.edu/busboyproblem for code and supplemental materials.