manjunath5496/motion-planning-papers

"In the end, it all comes down to 0 and 1."― Vineet Goel

Motion planning, also path planning (also known as the navigation problem or the piano mover's problem) is computational problem to find a sequence of valid configurations that moves the object from the source to destination. The term is used in computational geometry, computer animation, robotics and computer games.

For example, consider navigating a mobile robot inside a building to a distant waypoint. It should execute this task while avoiding walls and not falling down stairs. A motion planning algorithm would take a description of these tasks as input, and produce the speed and turning commands sent to the robot's wheels. Motion planning algorithms might address robots with a larger number of joints (e.g., industrial manipulators), more complex tasks (e.g. manipulation of objects), different constraints (e.g., a car that can only drive forward), and uncertainty (e.g. imperfect models of the environment or robot).

Motion planning has several robotics applications, such as autonomy, automation, and robot design in CAD software, as well as applications in other fields, such as animating digital characters, video game, artificial intelligence, architectural design, robotic surgery, and the study of biological molecules.

Papers

• CAD²RL: Real Single-Image Flight Without a Single Real Image
• STRIPS Planning in Infinite Domains
• Socially Aware Motion Planning with Deep Reinforcement Learning
• Learning Sampling Distributions for Robot Motion Planning
• PDDLStream: Integrating Symbolic Planners and Blackbox Samplers via Optimistic Adaptive Planning
• Complex-YOLO: An Euler-Region-Proposal for Real-time 3D Object Detection on Point Clouds
• Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
• Motion Planning Networks
• Egocentric Vision-based Future Vehicle Localization for Intelligent Driving Assistance Systems
• Deeply Informed Neural Sampling for Robot Motion Planning
• Learning Latent Dynamics for Planning from Pixels
• Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior
• Efficient Motion Planning for Automated Lane Change based on Imitation Learning and Mixed-Integer Optimization
• 3D BAT: A Semi-Automatic, Web-based 3D Annotation Toolbox for Full-Surround, Multi-Modal Data Streams
• BayesSim: adaptive domain randomization via probabilistic inference for robotics simulators
• Online Mixed-Integer Optimization in Milliseconds
• Learning to combine primitive skills: A step towards versatile robotic manipulation
• miniSAM: A Flexible Factor Graph Non-linear Least Squares Optimization Framework
• Motion Planning Explorer: Visualizing Local Minima using a Local-Minima Tree
• Control Synthesis from Linear Temporal Logic Specifications using Model-Free Reinforcement Learning
• Plan2vec: Unsupervised Representation Learning by Latent Plans
• Neural Contraction Metrics for Robust Estimation and Control: A Convex Optimization Approach
• Motion Planning Networks: Bridging the Gap Between Learning-based and Classical Motion Planners