Search for: All records

Robots deployed in many real-world settings need to be able to acquire new skills and solve new tasks over time. Prior works on planning with skills often make assumptions on the structure of skills and tasks, such as subgoal skills, shared skill implementations, or task-specific plan skeletons, which limit adaptation to new skills and tasks. By contrast, we propose doing task planning by jointly searching in the space of parameterized skills using high-level skill effect models learned in simulation. We use an iterative training procedure to efficiently generate relevant data to train such models. Our approach allows flexible skill parameterizations and task specifications to facilitate lifelong learning in general-purpose domains. Experiments demonstrate the ability of our planner to integrate new skills in a lifelong manner, finding new task strategies with lower costs in both train and test tasks. We additionally show that our method can transfer to the real world without further fine-tuning. 

Modelling and learning the dynamics of intricate dynamic interactions prevalent in common tasks such as push- ing a heavy door or picking up an object in one sweeping motion is a challenging problem. One needs to consider both the dynamics of the individual objects and of the interactions among objects. In this work, we present a method that enables efficient learning of the dynamics of interacting systems by simultaneously learning a dynamic graph structure and a stable and locally linear forward dynamic model of the system. The dynamic graph structure encodes evolving contact modes along a trajectory by making probabilistic predictions over the edge activations. Introducing a temporal dependence in the learned graph structure enables incorporating contact measurement updates which allows for more accurate forward predictions. The learned stable and locally linear dynamics enable the use of optimal control algorithms such as iLQR for long-horizon planning and control for complex interactive tasks. Through experiments in simulation and in the real world, we evaluate the performance of our method by using the learned inter- action dynamics for control and demonstrate generalization to more objects and interactions not seen during training. We also introduce a control scheme that takes advantage of contact measurement updates and hence is robust to prediction inaccuracies during execution. 

Training robotic policies in simulation suffers from the sim-to-real gap, as simulated dynamics can be different from real-world dynamics. Past works tackled this problem through domain randomization and online system-identification. The former is sensitive to the manually-specified training distribution of dynamics parameters and can result in behaviors that are overly conservative. The latter requires learning policies that concurrently perform the task and generate useful trajectories for system identification. In this work, we propose and analyze a framework for learning exploration policies that explicitly perform task-oriented exploration actions to identify task-relevant system parameters. These parameters are then used by model-based trajectory optimization algorithms to perform the task in the real world. We instantiate the framework in simulation with the Linear Quadratic Regulator as well as in the real world with pouring and object dragging tasks. Experiments show that task-oriented exploration helps model-based policies adapt to systems with initially unknown parameters, and it leads to better task performance than task-agnostic exploration.