Motion planning with sequential convex optimization and convex collision checking

By John Schulman, Yan Duan, Jonathan Ho, Alex X. Lee, Ibrahim Awwal, Henry Bradlow, Jia Pan, Sachin Patil, Ken Goldberg, Pieter Abbeel. 2014

1,002 citations recorded by the source corpus.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Control and Systems Engineering, Mathematical Optimization, Robotics & Control

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Mathematical Optimization

In Robotics & Control

Citations in the corpus

Habitat 2.0: Training Home Assistants to Rearrange their Habitat (2021, background): “[87] John Schulman, Yan Duan, Jonathan Ho, Alex Lee, Ibrahim Awwal, Henry Bradlow, Jia Pan, Sachin Patil, Ken Goldberg, and Pieter Abbeel.”
Reward-rational (implicit) choice: A unifying formalism for reward learning (2020, methodology): “Robotic motion planners cannot, in general, compute the globally optimal trajectory for a given θ ∈ Θ so we resort to computing a set ˆ T of locally optimal trajectories for each θ via TrajOpt [Schulman et al., 2014].”
acados—a modular open-source framework for fast embedded optimal control (2019, methodology): “There exist many algorithms for embedded optimal control and quite a few were successfully applied to realtime and embedded applications such as robotic trajectory optimization [83], autonomous driving [62] and drones [46].”
Asymptotically optimal sampling-based kinodynamic planning (2014, background): “There has been progress along this direction (Schulman et al., 2014; Zucker et al., 2013), although highly dynamic problems are still challenging.”
Learning Robot Objectives from Physical Human Interaction (2017, positive): “We use a trajectory optimizer [18] to replan the robot’s desired trajectory ξ R ξ R = arg max ξ θ̂ · Φ(ξ) (4)”
RAPTOR: Robust and Perception-Aware Trajectory Replanning for Quadrotor Fast Flight (2020, background): “Previous work [39] showed that failure of GTO is relevant to unfavorable initialization, i.e., initial paths that pass through obstacles in certain ways usually get stuck.”
Integrated Task and Motion Planning (2020, methodology): “The most eﬀective methods are based on sampling (4, 5) or constrained optimization (6, 7).”
Guiding Trajectory Optimization by Demonstrated Distributions (2017, methodology): “Although sampling-based methods can deal with complex path planning scenarios, these methods are computationally inefficient compared to optimization-based methods [3], [4].”
Voxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning (2016, background): “simpliﬁed sensor model. However, there are planning approaches for which only occupancy information is insufﬁcient. For example, trajectory optimization-based planners, such as CHOMP [11] and TrajOpt [12], require distances to obstacles and collision gradient information. This requires distance info”
Spatial adaption of robot trajectories based on laplacian trajectory editing (2015, methodology): “Closely related to this approach are explicit trajectory optimization schemes as CHOMP or TrajOpt (Zucker et al (2013); Schulman et al (2014)).”