• Publications
  • Influence
Sampling-based algorithms for optimal motion planning
The main contribution of the paper is the introduction of new algorithms, namely, PRM and RRT*, which are provably asymptotically optimal, i.e. such that the cost of the returned solution converges almost surely to the optimum.
Incremental Sampling-based Algorithms for Optimal Motion Planning
A new algorithm is considered, called the Rapidly-exploring Random Graph (RRG), and it is shown that the cost of the best path returned by RRG converges to the optimum almost surely, and a tree version of RRG is introduced, called RRT∗, which preserves the asymptotic optimality ofRRG while maintaining a tree structure like RRT.
Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
  • Fangchang Ma, S. Karaman
  • Computer Science, Engineering
    IEEE International Conference on Robotics and…
  • 21 September 2017
The use of a single deep regression network to learn directly from the RGB-D raw data is proposed, and the impact of number of depth samples on prediction accuracy is explored, to attain a higher level of robustness and accuracy.
Self-Supervised Sparse-to-Dense: Self-Supervised Depth Completion from LiDAR and Monocular Camera
A deep regression model is developed to learn a direct mapping from sparse depth (and color images) input to dense depth prediction and a self-supervised training framework that requires only sequences of color and sparse depth images, without the need for dense depth labels is proposed.
Anytime Motion Planning using the RRT*
This paper presents two key extensions to the RRT*, committed trajectories and branch-and-bound tree adaptation, that together enable the algorithm to make more efficient use of computation time online, resulting in an anytime algorithm for real-time implementation.
Real-Time Motion Planning With Applications to Autonomous Urban Driving
The proposed algorithm was at the core of the planning and control software for Team MIT's entry for the 2007 DARPA Urban Challenge, where the vehicle demonstrated the ability to complete a 60 mile simulated military supply mission, while safely interacting with other autonomous and human driven vehicles.
Optimal kinodynamic motion planning using incremental sampling-based methods
It is shown that the RRT* algorithm equipped with any local steering procedure that satisfies this condition converges to an optimal solution almost surely, while maintaining the same properties of the standard RRT algorithm.
FastDepth: Fast Monocular Depth Estimation on Embedded Systems
This paper proposes an efficient and lightweight encoder-decoder network architecture and applies network pruning to further reduce computational complexity and latency and demonstrates real-time monocular depth estimation using a deep neural network with the lowest latency and highest throughput on an embedded platform that can be carried by a micro aerial vehicle.
Sampling-based motion planning with deterministic μ-calculus specifications
Algorithms for the on-line computation of control programs for dynamical systems that provably satisfy a class of temporal logic specifications are proposed, generalizing state-of-the-art algorithms for point-to-point motion planning.
Sampling-based optimal motion planning for non-holonomic dynamical systems
The RRT* algorithm is extended to handle a large class of non-holonomic dynamical systems, and the performance of the algorithm is demonstrated in computational experiments involving the Dubins' car dynamics.