Model-based control faces fundamental challenges in partially-observable environments due to unmodeled obstacles. We propose an online learning and optimization method to identify and avoid unobserved obstacles online. Our method, Constraint Obeying Gaussian Implicit Surfaces (COGIS), infers contact data using a combination of visual input and state tracking, informed by predictions from a nominal dynamics model. We then fit a Gaussian process implicit surface (GPIS) to these data and refine the dataset through a novel method of enforcing constraints on the estimated surface. This allows us to design a Model Predictive Control (MPC) method that leverages the obstacle estimate to complete multiple manipulation tasks. By modeling the environment instead of attempting to directly adapt the dynamics, our method succeeds at both low-dimensional peg-in-hole tasks and high-dimensional deformable object manipulation tasks. Our method succeeds in 10/10 trials vs 1/10 for a baseline on a real-world cable manipulation task under partial observability of the environment.

Robotic manipulation of deformable, one-dimensional objects (DOOs) like ropes or cables has important potential applications in manufacturing, agriculture, and surgery. In such environments, the task may involve threading through or avoiding becoming tangled with objects like racks or frames. Grasping with multiple grippers can create closed loops between the robot and DOO, and If an obstacle lies within this loop, it may be impossible to reach the goal. However, prior work has only considered the topology of the DOO in isolation, ignoring the arms that are manipulating it. Searching over possible grasps to accomplish the task without considering such topological information is very inefficient, as many grasps will not lead to progress on the task due to topological constraints. Therefore, we propose a grasp loop signature which categorizes the topology of these grasp loops and show how it can be used to guide planning. We perform experiments in simulation on two DOO manipulation tasks to show that using the signature is faster and succeeds more often than methods that rely on local geometry or finite-horizon planning. Finally, we demonstrate using the signature in the real world to manipulate a cable in a scene with obstacles using a dual-arm robot.

In order to efficiently learn a dynamics model for a task in a new environment, one can adapt a model learned in a similar source environment. However, existing adaptation methods can fail when the target dataset contains transitions where the dynamics are very different from the source environment. For example, the source environment dynamics could be of a rope manipulated in free space, whereas the target dynamics could involve collisions and deformation on obstacles. Our key insight is to improve data efficiency by focusing model adaptation on only the regions where the source and target dynamics are similar. In the rope example, adapting the free-space dynamics requires significantly less data than adapting the free-space dynamics while also learning collision dynamics. We propose a new method for adaptation that is effective in adapting to regions of similar dynamics. Additionally, we combine this adaptation method with prior work on planning with unreliable dynamics to make a method for data-efficient online adaptation, called FOCUS. We first demonstrate that the proposed adaptation method achieves statistically significantly lower prediction error in regions of similar dynamics on simulated rope manipulation and plant watering tasks. We then show on a bimanual rope manipulation task that FOCUS achieves data-efficient online learning, in simulation and in the real world.

The success of deep learning depends heavily on the availability of large datasets, but in robotic manipulation there are many learning problems for which such datasets do not exist. Collecting these datasets is time-consuming and expensive, and therefore learning from small datasets is an important open problem. Within computer vision, a common approach to a lack of data is data augmentation. Data augmentation is the process of creating additional training examples by modifying existing ones. However, because the types of tasks and data differ, the methods used in computer vision cannot be easily adapted to manipulation. Therefore, we propose a data augmentation method for robotic manipulation. We argue that augmentations should be valid, relevant, and diverse. We use these principles to formalize augmentation as an optimization problem, with the objective function derived from physics and knowledge of the manipulation domain. This method applies rigid body transformations to trajectories of geometric state and action data. We test our method in two scenarios: 1) learning the dynamics of planar pushing of rigid cylinders, and 2) learning a constraint checker for rope manipulation. These two scenarios have different data and label types, yet in both scenarios, training on our augmented data significantly improves performance on downstream tasks. We also show how our augmentation method can be used on real-robot data to enable more data-efficient online learning.

The world outside our laboratories seldom conforms to the assumptions of our models. This is especially true for dynamics models used in control and motion planning for complex high-degree of freedom systems like deformable objects. We must develop better models, but we must also consider that, no matter how powerful our simulators or how big our datasets, our models will sometimes be wrong. What is more, estimating how wrong models are can be difficult, because methods that predict uncertainty distributions based on training data do not account for unseen scenarios. To deploy robots in unstructured environments, we must address two key questions: When should we trust a model and what do we do if the robot is in a state where the model is unreliable. We tackle these questions in the context of planning for manipulating rope-like objects in clutter. Here, we report an approach that learns a model in an unconstrained setting and then learns a classifier to predict where that model is valid, given a limited dataset of rope-constraint interactions. We also propose a way to recover from states where our model prediction is unreliable. Our method statistically significantly outperforms learning a dynamics function and trusting it everywhere. We further demonstrate the practicality of our method on real-world mock-ups of several domestic and automotive tasks.

When the dynamics of a system are difficult to model and/or time-consuming to evaluate, such as in deformable object manipulation tasks, motion planning algorithms struggle to find feasible plans efficiently. Such problems are often reduced to state spaces where the dynamics are straightforward to model and evaluate. However, such reductions usually discard information about the system for the benefit of computational efficiency, leading to cases where the true and reduced dynamics disagree on the result of an action. This letter presents a formulation for planning in reduced state spaces that uses a classifier to bias the planner away from state-action pairs that are not reliably feasible under the true dynamics. We present a method to generate and label data to train such a classifier, as well as an application of our framework to rope manipulation, where we use a Virtual Elastic Band (VEB) approximation to the true dynamics. Our experiments with rope manipulation demonstrate that the classifier significantly improves the success rate of our RRT-based planner in several difficult scenarios which are designed to cause the VEB to produce incorrect predictions in key parts of the environment.

We present a decentralized algorithm to achieve segregation into an arbitrary number of groups with swarms of autonomous robots. The distinguishing feature of our approach is in the minimalistic assumptions on which it is based. Specifically, we assume that (i) Each robot is equipped with a ternary sensor capable of detecting the presence of a single nearby robot, and, if that robot is present, whether or not it belongs to the same group as the sensing robot; (ii) The robots move according to a differential drive model; and (iii) The structure of the control system is purely reactive, and it maps directly the sensor readings to the wheel speeds with a simple `if' statement. We present a thorough analysis of the parameter space that enables this behavior to emerge, along with an analysis that explains the emergent behavior. Finally, we study the effect on segregation performance of some nonideal aspects in the robot morphology.