High degree-of-freedom dual-arm robots are becoming increasingly common due to their morphology enabling them to operate effectively in human environments. However, motion planning in real-time within unknown, changing environments remains a challenge for such robots due to the high dimensionality of the configuration space and the complex collision-avoidance constraints that must be obeyed. In this work, we propose a novel way to alleviate the curse of dimensionality by leveraging the structure imposed by shared joints (e.g. torso joints) in a dual-arm robot. First, we build two dynamic roadmaps (DRM) for each kinematic chain (i.e. left arm + torso, right arm + torso) with specific structure induced by the shared joints. Then, we show that we can leverage this structure to efficiently search through the composition of the two roadmaps and largely sidestep the curse of dimensionality. Finally, we run several experiments in a real-world grocery store with this motion planner on a 19 DoF mobile manipulation robot executing a grocery fulfillment task, achieving 0.4s average planning times with 99.9% success rate across more than 2000 motion plans.

We present a solution to the separate challenges faced by suction cups and gecko adhesives for one-sided grasping of heavy, irregular items. The gripping technology combines suction with adhesion for grasping and placing a wide range of objects in packed spaces. Applications include shopping and restocking in retail and warehouse settings where products vary in size and weight and are packed tightly, which limits access. A single suction cup is compact enough to reach and grasp the smallest items (down to 5 cm in size) but cannot provide the shear force needed for handling bulky items. Gecko-inspired adhesion provides extra lifting capability for objects up to 2.3 kg, using a 7.6 × 12.7 cm adhesive swatch −2.5x heavier than with suction alone. The adhesive is fabricated on a flexible nylon fabric. A small fan blows gently to help the fabric conform to irregular surfaces prior to lifting.

We present our general-purpose mobile manipulation system consisting of a custom robot platform and key algorithms spanning perception and planning. To extensively test the system in the wild and benchmark its performance, we choose a grocery shopping scenario in an actual, unmodified grocery store. We derive key performance metrics from detailed robot log data collected during six week-long field tests, spread across 18 months. These objective metrics, gained from complex yet repeatable tests, drive the direction of our research efforts and let us continuously improve our system's performance. We find that thorough end-to-end system-level testing of a complex mobile manipulation system can serve as a reality-check for state-of-the-art methods in robotics. This effectively grounds robotics research efforts in real world needs and challenges, which we deem highly useful for the advancement of the field. To this end, we share our key insights and takeaways to inspire and accelerate similar system-level research projects.

In this paper, we achieve reliable, sub-second motion planning to Cartesian end-effector targets in changing real-world environments for a high degree-of-freedom $(\mathbf{12} + \mathbf{7}$ DoF), redundant robot. Several recent works have tackled a subset of these challenges, leveraging innovations in optimization, deep learning, and/or intelligent sampling. However, deployment of robots in real-world environments demands reliably tackling all three challenges: changing environments, fast planning, and high DoF robots. In this work, we leverage (1) large-scale Dynamic Roadmaps (DRM) enabled through GPU-accelerated collision-checking, combined with (2) an optimization-based local inverse kinematics (IK) solver. The high-level principle behind our approach is to offload as much computation either offline or onto the GPU as possible in order to simplify and speed up online planning. Even in changing environments, this enables fast planning in configuration space to a neighborhood of a target pose(s) specified in Cartesian space, whereby the final connection to the target pose is made via a local IK solver. We ran several experiments in an unmodified real-world grocery store with this motion planner on a $\mathbf{12} + \mathbf{7}$ DoF mobile manipulation robot executing a grocery fulfillment task, achieving ≈0.3s average planning times with 100% success rate across 950 motion plans.