arXiv subjects

Manuel Baum

Publications and source records attributed to Manuel Baum.

4 recordsLinked to original sources

arXiv2026

Robustness of Robotic Manipulation: Foundations and Frontiers

Humans and animals exhibit remarkable robustness in physical manipulation, yet robots remain far behind. Progress toward human-level manipulation robustness is hindered by the absence of a unified and systematic understanding: different subfields frame robustness in distinct ways, often leaving the concept ambiguous and limiting deeper analysis as well as communication across research areas. This paper presents a systematic study of manipulation robustness. We begin with a formal definition, characterizing robustness as the degree to which a manipulation system can achieve its goal in the presence of uncertainty and variation. Building on this definition, we introduce general formulations of manipulation robustness from probabilistic and control-theoretic perspectives. We then synthesize the guiding principles and concrete mechanisms of manipulation robustness across perception, planning, control, policy learning, and hardware, illustrating each mechanism through representative works, including foundational and recent studies. In addition, we revisit existing metrics and evaluation methods for quantifying manipulation robustness. Finally, we distill broader lessons for designing robust manipulation systems and discuss open problems and future directions toward achieving human-level robustness in robotic manipulation.

cs.RO↗

arXiv2024

Mechanical problem solving in Goffin's cockatoos -- Towards modeling complex behavior

Research continues to accumulate evidence that Goffin's cockatoos (Cacatua goffiniana) can solve wide sets of mechanical problems, such as tool use, tool manufacture, and solving mechanical puzzles. However, the proximate mechanisms underlying this adaptive behavior are largely unknown. In this study, we analyze how three Goffin's cockatoos learn to solve a specific mechanical puzzle, a lockbox. The observed behavior results from the interaction between a complex environment (the lockbox) and different processes that jointly govern the animals' behavior. We thus jointly analyze the parrots' (1) engagement, (2) sensorimotor skill learning, and (3) action selection. We find that neither of these aspects could solely explain the animals' behavioral adaptation and that a plausible model of proximate mechanisms (including adaptation) should thus also jointly address these aspects. We accompany this analysis with a discussion of methods that may be used to identify such mechanisms. A major point we want to make is, that it is implausible to reliably identify a detailed model from the limited data of one or a few studies. Instead, we advocate for a more coarse approach that first establishes constraints on proximate mechanisms before specific, detailed models are formulated. We exercise this idea on the data we present in this study.

q-bio.NC↗

arXiv2022

Augmentation for Learning From Demonstration with Environmental Constraints

We introduce a Learning from Demonstration (LfD) approach for contact-rich manipulation tasks with articulated mechanisms. The extracted policy from a single human demonstration generalizes to different mechanisms of the same type and is robust against environmental variations. The key to achieving such generalization and robustness from a single human demonstration is to autonomously augment the initial demonstration to gather additional information through purposefully interacting with the environment. Our real-world experiments on complex mechanisms with multi-DOF demonstrate that our approach can reliably accomplish the task in a changing environment. Videos are available at the: https://sites.google.com/view/rbosalfdec/home

cs.RO↗

arXiv2022

"The World Is Its Own Best Model": Robust Real-World Manipulation Through Online Behavior Selection

Robotic manipulation behavior should be robust to disturbances that violate high-level task-structure. Such robustness can be achieved by constantly monitoring the environment to observe the discrete high-level state of the task. This is possible because different phases of a task are characterized by different sensor patterns and by monitoring these patterns a robot can decide which controllers to execute in the moment. This relaxes assumptions about the temporal sequence of those controllers and makes behavior robust to unforeseen disturbances. We implement this idea as probabilistic filter over discrete states where each state is direcly associated with a controller. Based on this framework we present a robotic system that is able to open a drawer and grasp tennis balls from it in a surprisingly robust way.

cs.RO↗