Leveraging Building Material as Part of the In-Plane Robotic Kinematic System for Collective Construction.

Although collective robotic construction systems are beginning to showcase how multi-robot systems can contribute to building construction by efficiently building low-cost, sustainable structures, the majority of research utilizes non-structural or highly customized materials. A modular collective robotic construction system based on a robotic actuator, which leverages timber struts for the assembly of architectural artifacts as well as part of the robot body for locomotion is presented. The system is co-designed for in-plane assembly from an architectural, robotic, and computer science perspective in order to integrate the various hardware and software constraints into a single workflow. The system is tested using five representative physical scenarios. These proof-of-concept demonstrations showcase three tasks required for construction assembly: the ability of the system to locomote, dynamically change the topology of connecting robotic actuators and timber struts, and collaborate to transport timber struts. As such, the groundwork for a future autonomous collective robotic construction system that could address collective construction assembly and even further increase the flexibility of on-site construction robots through its modularity is laid.

Optimality Principles in Human Point-to-Manifold Reaching Accounting for Muscle Dynamics.

Human arm movements are highly stereotypical under a large variety of experimental conditions. This is striking due to the high redundancy of the human musculoskeletal system, which in principle allows many possible trajectories toward a goal. Many researchers hypothesize that through evolution, learning, and adaption, the human system has developed optimal control strategies to select between these possibilities. Various optimality principles were proposed in the literature that reproduce human-like trajectories in certain conditions. However, these studies often focus on a single cost function and use simple torque-driven models of motion generation, which are not consistent with human muscle-actuated motion. The underlying structure of our human system, with the use of muscle dynamics in interaction with the control principles, might have a significant influence on what optimality principles best model human motion. To investigate this hypothesis, we consider a point-to-manifold reaching task that leaves the target underdetermined. Given hypothesized motion objectives, the control input is generated using Bayesian optimization, which is a machine learning based method that trades-off exploitation and exploration. Using numerical simulations with Hill-type muscles, we show that a combination of optimality principles best predicts human point-to-manifold reaching when accounting for the muscle dynamics.

Preferred Interaction Styles for Human-Robot Collaboration Vary Over Tasks With Different Action Types.

How do humans want to interact with collaborative robots? As robots become more common and useful not only in industry but also in the home, they will need to interact with humans to complete many varied tasks. Previous studies have demonstrated that autonomous robots are often more efficient and preferred over those that need to be commanded, or those that give instructions to humans. We believe that the types of actions that make up a task affect the preference of participants for different interaction styles. In this work, our goal is to explore tasks with different action types together with different interaction styles to find the specific situations in which different interaction styles are preferred. We have identified several classifications for table-top tasks and have developed a set of tasks that vary along two of these dimensions together with a set of different interaction styles that the robot can use to choose actions. We report on results from a series of human-robot interaction studies involving a PR2 completing table-top tasks with a human. The results suggest that people prefer robot-led interactions for tasks with a higher cognitive load and human-led interactions for joint actions.

No free lunch in ball catching: A comparison of Cartesian and angular representations for control.

How to run most effectively to catch a projectile, such as a baseball, that is flying in the air for a long period of time? The question about the best solution to the ball catching problem has been subject to intense scientific debate for almost 50 years. It turns out that this scientific debate is not focused on the ball catching problem alone, but revolves around the research question what constitutes the ingredients of intelligent decision making. Over time, two opposing views have emerged: the generalist view regarding intelligence as the ability to solve any task without knowing goal and environment in advance, based on optimal decision making using predictive models; and the specialist view which argues that intelligent decision making does not have to be based on predictive models and not even optimal, advocating simple and efficient rules of thumb (heuristics) as superior to enable accurate decisions. We study two types of approaches to the ball catching problem, one for each view, and investigate their properties using both a theoretical analysis and a broad set of simulation experiments. Our study shows that neither of the two types of approaches can be regarded as superior in solving all relevant variants of the ball catching problem: each approach is optimal under a different realistic environmental condition. Therefore, predictive models neither guarantee nor prevent success a priori, and we further show that the key difference between the generalist and the specialist approach to ball catching is the type of input representation used to control the agent. From this finding, we conclude that the right solution to a decision making or control problem is orthogonal to the generalist and specialist approach, and thus requires a reconciliation of the two views in favor of a representation-centric view.

Planning as inference.

Recent developments in decision-making research are bringing the topic of planning back to center stage in cognitive science. This renewed interest reopens an old, but still unanswered question: how exactly does planning happen? What are the underlying information processing operations and how are they implemented in the brain? Although a range of interesting possibilities exists, recent work has introduced a potentially transformative new idea, according to which planning is accomplished through probabilistic inference.

Learned graphical models for probabilistic planning provide a new class of movement primitives.

BIOLOGICAL MOVEMENT GENERATION COMBINES THREE INTERESTING ASPECTS: its modular organization in movement primitives (MPs), its characteristics of stochastic optimality under perturbations, and its efficiency in terms of learning. A common approach to motor skill learning is to endow the primitives with dynamical systems. Here, the parameters of the primitive indirectly define the shape of a reference trajectory. We propose an alternative MP representation based on probabilistic inference in learned graphical models with new and interesting properties that complies with salient features of biological movement control. Instead of endowing the primitives with dynamical systems, we propose to endow MPs with an intrinsic probabilistic planning system, integrating the power of stochastic optimal control (SOC) methods within a MP. The parameterization of the primitive is a graphical model that represents the dynamics and intrinsic cost function such that inference in this graphical model yields the control policy. We parameterize the intrinsic cost function using task-relevant features, such as the importance of passing through certain via-points. The system dynamics as well as intrinsic cost function parameters are learned in a reinforcement learning (RL) setting. We evaluate our approach on a complex 4-link balancing task. Our experiments show that our movement representation facilitates learning significantly and leads to better generalization to new task settings without re-learning.

Complex adaptation and system structure.

The structural organization of biological systems is one of nature's most fascinating aspects, but its origin and functional role is not yet fully understood. For instance, basic adaptational mechanisms like genetic mutation and Hebbian adaptation seem to be generic and invariant across many species and are, on their own, fairly well investigated and understood. However, it is the organism's structure - the representations these mechanisms act upon - that bears the complex functional effects of these mechanisms. While typical technical approaches to system design require detailed problem models and suffer from the need to explicitly take care of all possible cases, the organization of biological systems seems to induce inherent adaptability, flexibility and robustness. In this discussion paper we address the concept of structured variability, particularly the role of system structure as implementing a certain representation on which basic variational mechanisms act on. The functional adaptability (or search distribution) depends crucially on this representation.

A sensorimotor map: modulating lateral interactions for anticipation and planning.

Experimental studies of reasoning and planned behavior have provided evidence that nervous systems use internal models to perform predictive motor control, imagery, inference, and planning. Classical (model-free) reinforcement learning approaches omit such a model; standard sensorimotor models account for forward and backward functions of sensorimotor dependencies but do not provide a proper neural representation on which to realize planning. We propose a sensorimotor map to represent such an internal model. The map learns a state representation similar to self-organizing maps but is inherently coupled to sensor and motor signals. Motor activations modulate the lateral connection strengths and thereby induce anticipatory shifts of the activity peak on the sensorimotor map. This mechanism encodes a model of the change of stimuli depending on the current motor activities. The activation dynamics on the map are derived from neural field models. An additional dynamic process on the sensorimotor map (derived from dynamic programming) realizes planning and emits corresponding goal-directed motor sequences, for instance, to navigate through a maze.