In this work we tackle the path planning problem for a 21-dimensional snake robot-like manipulator, navigating a cluttered gas turbine for the purposes of inspection. Heuristic search based approaches are effective planning strategies for common manipulation domains. However, their performance on high dimensional systems is heavily reliant on the effectiveness of the action space and the heuristics chosen. The complex nature of our system, reachability constraints, and highly cluttered turbine environment renders naive choices of action spaces and heuristics ineffective. To this extent we have developed i) a methodology for dynamically generating actions based on online optimization that help the robot navigate narrow spaces, ii) a technique for lazily generating these computationally expensive optimization actions to effectively utilize resources, and iii) heuristics that reason about the homotopy classes induced by the blades of the turbine in the robot workspace and a Multi-Heuristic framework which guides the search along the relevant classes. The impact of our contributions is presented through an experimental study in simulation, where the 21 DOF manipulator navigates towards regions of inspection within a turbine.

Heuristic-based graph search algorithms like A* are frequently used to solve motion planning problems in many domains. For most practical applications, it is infeasible and unnecessary to pre-compute the graph representing the whole search space. Instead, these algorithms generate the graph incrementally by applying a fixed set of actions (frequently called motion primitives) to find the successors of every node that they need to evaluate. In many domains, it is possible to define actions (called adaptive motion primitives) that are not pre-computed but generated on the fly. The generation and validation of these adaptive motion primitives is usually quite expensive compared to pre-computed motion primitives. However, they have been shown to drastically speed up search if used judiciously. In prior work, ad hoc techniques like fixed thresholds have been used to limit unsuccessful evaluations of these actions. In this paper, we propose a learning-based approach to make more intelligent decisions about when to evaluate them. We do a thorough empirical evaluation of our model on a 3 degree-of-freedom (dof) motion planning problem for navigation using the Reeds-Shepp path as an adaptive motion primitive. Our experiments show that using our approach in conjunction with search algorithms leads to over 2x speedup in planning time.

A core requirement of database engine testing is the ability to create synthetic versions of the customer’s data warehouse at the vendor site. A rich body of work exists on synthetic database regeneration, but suffers critical limitations with regard to: (a) maintaining statistical fidelity to the client’s query processing, and/or (b) scaling to large data volumes. In this paper, we present HYDRA, a workload-dependent database regenerator that leverages a declarative approach to data regeneration to assure volumetric similarity, a crucial aspect of statistical fidelity, and materially improves on the prior art by adding scale, dynamism and functionality. Specifically, Hydra uses an optimized linear programming (LP) formulation based on a novel regionpartitioning approach. This spatial strategy drastically reduces the LP complexity, enabling it to handle query workloads on which contemporary techniques fail. Second, Hydra incorporates deterministic post-LP processing algorithms that provide high efficiency and improved accuracy. Third, Hydra introduces the concept of dynamic regeneration by constructing a minuscule database summary that can on-the-fly regenerate databases of arbitrary size during query execution, while obeying volumetric specifications derived from the query workload. A detailed experimental evaluation on standard OLAP benchmarks demonstrates that Hydra can efficiently and dynamically regenerate large warehouses that accurately mimic the desired statistical characteristics.

A core requirement of database engine testing is the ability to create synthetic versions of the customer's data warehouse at the vendor site. Prior work on synthetic data regeneration suffers from critical limitations with regard to (a) scaling to large data volumes, (b) handling complex query workloads, and (c) producing data on demand. In this demo, we present HYDRA , a workload-dependent dynamic data regenerator, that materially addresses these limitations. It introduces the concept of dynamic regeneration by constructing a minuscule memory-resident database summary that can on-the-fly regenerate databases of arbitrary size during query execution. Further, since the data is generated in memory, the velocity of generation can be closely regulated. Finally, to complement dynamic regeneration, Hydra also ensures that the process of summary construction is data-scale-free.