Hybrid control trajectory optimization under uncertainty

Trajectory optimization is a fundamental problem in robotics. While optimization of continuous control trajectories is well developed, many applications require both discrete and continuous, i.e., hybrid, controls. Finding an optimal sequence of hybrid controls is challenging due to the exponential explosion of discrete control combinations. Our method, based on Differential Dynamic Programming (DDP), circumvents this problem by incorporating discrete actions inside DDP: we first optimize continuous mixtures of discrete actions, and, subsequently force the mixtures into fully discrete actions. Moreover, we show how our approach can be extended to partially observable Markov decision processes (POMDPs) for trajectory planning under uncertainty. We validate the approach in a car driving problem where the robot has to switch discrete gears and in a box pushing application where the robot can switch the side of the box to push. The pose and the friction parameters of the pushed box are initially unknown and only indirectly observable.


Similar Publications

Tensegrity mechanisms have several interesting properties that make them suitable for a number of applications. Their analysis is generally challenging because the static equilibrium conditions often result in complex equations. A class of planar one-degree-of-freedom (dof) tensegrity mechanisms with three linear springs is analyzed in detail in this paper. Read More


A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a sequence of actions from visual observations that transform a dynamic environment from an initial state to a goal state. Doing so entails knowledge about objects and their affordances, as well as actions and their preconditions and effects. Read More


This paper highlights the significance of including memory structures in neural networks when the latter are used to learn perception-action loops for autonomous robot navigation. Traditional navigation approaches rely on global maps of the environment to overcome cul-de-sacs and plan feasible motions. Yet, maintaining an accurate global map may be challenging in real-world settings. Read More


We present an efficient path planning algorithm for an Unmanned Aerial Vehicle surveying a cluttered urban landscape. A special emphasis is on maximizing area surveyed while adhering to constraints of the UAV and partially known and updating environment. A Voronoi bias is introduced in the probabilistic roadmap building phase to identify certain critical milestones for maximal surveillance of the search space. Read More


In the adaptive information gathering problem, a policy is required to select an informative sensing location using the history of measurements acquired thus far. While there is an extensive amount of prior work investigating effective practical approximations using variants of Shannon's entropy, the efficacy of such policies heavily depends on the geometric distribution of objects in the world. On the other hand, the principled approach of employing online POMDP solvers is rendered impractical by the need to explicitly sample online from a posterior distribution of world maps. Read More


This paper presents a motion planner for systems subject to kinematic and dynamic constraints. The former appear when kinematic loops are present in the system, such as in parallel manipulators, in robots that cooperate to achieve a given task, or in situations involving contacts with the environment. The latter are necessary to obtain realistic trajectories, taking into account the forces acting on the system. Read More


Validation of robotics theory on real-world hardware platforms is important to prove the practical feasibility of algorithms. This paper discusses some of the lessons learned while adapting the EvoBot, a low-cost robotics platform that we designed and prototyped, for research in diverse areas in robotics. The EvoBot platform was designed to be a low cost, open source, general purpose robotics platform intended to enable testing and validation of algorithms from a wide variety of sub-fields of robotics. Read More


This paper overviews certain radiation detection, perception, and planning challenges for nuclearized robotics that aim to support the waste management and decommissioning mission. To enable the autonomous monitoring, inspection and multi-modal characterization of nuclear sites, we discuss important problems relevant to the tasks of navigation in degraded visual environments, localizability-aware exploration and mapping without any prior knowledge of the environment, as well as robotic radiation detection. Future contributions will focus on each of the relevant problems, will aim to deliver a comprehensive multi-modal mapping result, and will emphasize on extensive field evaluation and system verification. Read More


Linking human whole-body motion and natural language is of great interest for the generation of semantic representations of observed human behaviors as well as for the generation of robot behaviors based on natural language input. While there has been a large body of research in this area, most approaches that exist today require a symbolic representation of motions (e.g. Read More


Reinforcement learning is a powerful technique to train an agent to perform a task. However, an agent that is trained using reinforcement learning is only capable of achieving the single task that is specified via its reward function. Such an approach does not scale well to settings in which an agent needs to perform a diverse set of tasks, such as navigating to varying positions in a room or moving objects to varying locations. Read More