Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This study explores the use of Star-World workspace reshaping to enhance the reactive 3D motion planning of a Franka Emika Panda manipulator, addressing the challenges posed by safety inflation and overlapping obstacles. By clustering intersecting inflated obstacles and replacing them with star-shaped proxies, the researchers evaluated the performance of this method against traditional unreshaped representations across six PyBullet scenarios. The results indicate that reshaping improved goal attainment in five out of six scenarios, although it also led to increased path lengths and some instances of near-equilibria, highlighting both its potential and limitations in practical applications.
Star-World reshaping boosts goal attainment in reactive motion planning, but at the cost of longer paths and unexpected equilibria.
Safety inflation can cause nearby obstacles to overlap, violating the disjoint-obstacle assumptions used by many modulation-based reactive planners. We investigate Star-World workspace reshaping for three-dimensional reactive control of a Franka Emika Panda manipulator. At each update, intersecting inflated obstacles are clustered and replaced by star-shaped proxies before a dynamical-system-based end-effector controller is evaluated. A null-space artificial-potential-field term provides complementary arm-body avoidance. We compare reshaped and unreshaped obstacle representations in six PyBullet scenarios using goal attainment, path-length ratio, and computation time. In this preliminary 12-trial evaluation, reshaping reaches the goal in five of six scenarios, compared with four of six for the unreshaped baseline. It resolves the canonical overlapping-wall case and requires 0.68--8.70\,ms per workspace update for scenes containing one to seven obstacles. However, it also increases path length, produces near-equilibria in two cases, and closes a navigable corridor through over-aggressive merging. These results show both the promise and the practical limitations of transferring Star-World guarantees from workspace geometry to a redundant manipulator controlled through inverse kinematics.