Abhishek Cauligi
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Abhishek Cauligi has a total of 90 co-authors. Here are the top co-authors by number of shared publications:
- Marco Pavone
Stanford University
3 shared publications - Bartolomeo Stellato
Department of Operations Research and Financial Engineering, Princeton University, Princeton, USA
2 shared publications - Mac Schwager
Department of Aeronautics and Astronautics, Stanford University, Stanford, CA, USA
2 shared publications - Preston Culbertson
Department of Mechanical and Civil Engineering, California Institute of Technology, Pasadena, CA, USA
2 shared publications - Abhishek Thakur
Aptiv, Troy, MI, USA
1 shared publication Alessandro Buscicchio
NASA Jet Propulsion Laboratory, California Institute of Technology; Polytechnic University of Bari
1 shared publication
Latest Publications
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 3, 177-200
CRESCENT: Collision-Free Highly Constrained Trajectory Optimization for Driving on the Moon
Rovers have been a mainstay of planetary exploration missions, significantly expanding our knowledge in planetary science. However, past rover missions have involved significant human supervision to oversee rover operations, a state-of-practice that scales poorly for the next generation of missions. In this work, we present the development of CRESCENT, a motion planning algorithm developed for the upcoming multi-agent CADRE Lunar rover mission. CRESCENT was designed to safely drive a miniature rover platform in a highly cluttered unmapped Lunar environment, executing complex motion directives from CADRE’s team-level autonomy while meeting far stricter dynamical and temporal constraints than existing on-board planetary rover planning algorithms are capable of satisfying. Our hierarchical approach formulates an efficient numerical trajectory optimization-based motion planning algorithm that makes use of nonlinear optimization to solve the planning problem in real-time. We demonstrate the efficiency of our proposed approach through extensive simulations and hardware testing in a representative Lunar environment. Following CADRE’s upcoming deployment on the Lunar surface, CRESCENT will be the first nonlinear optimization-based trajectory optimization approach used on another celestial body.
- 2 December 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 3, 177-200
CRESCENT: Collision-Free Highly Constrained Trajectory Optimization for Driving on the Moon
Rovers have been a mainstay of planetary exploration missions, significantly expanding our knowledge in planetary science. However, past rover missions have involved significant human supervision to oversee rover operations, a state-of-practice that scales poorly for the next generation of missions. In this work, we present the development of CRESCENT, a motion planning algorithm developed for the upcoming multi-agent CADRE Lunar rover mission. CRESCENT was designed to safely drive a miniature rover platform in a highly cluttered unmapped Lunar environment, executing complex motion directives from CADRE’s team-level autonomy while meeting far stricter dynamical and temporal constraints than existing on-board planetary rover planning algorithms are capable of satisfying. Our hierarchical approach formulates an efficient numerical trajectory optimization-based motion planning algorithm that makes use of nonlinear optimization to solve the planning problem in real-time. We demonstrate the efficiency of our proposed approach through extensive simulations and hardware testing in a representative Lunar environment. Following CADRE’s upcoming deployment on the Lunar surface, CRESCENT will be the first nonlinear optimization-based trajectory optimization approach used on another celestial body.
- 2 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 1, 213-230
ShadowNav: Autonomous Global Localization for Lunar Navigation in Darkness
The ability to determine the position of a rover in an inertial frame autonomously is a crucial capability necessary for the next generation of surface rover missions on other planetary bodies. Currently, most on-going rover missions utilize ground-in-the-loop interventions to manually correct for drift in the position estimate and this human supervision bottlenecks the distance over which rovers can operate autonomously and carry out scientific measurements. In this paper, we present ShadowNav, an autonomous approach for global 2D localization on the Moon with an emphasis on driving in darkness and at nighttime. Our approach uses the leading edge of Lunar craters as landmarks and a particle filtering approach to associate detected craters with known ones on an offboard map. We discuss the key design decisions in developing the ShadowNav framework for use with a Lunar rover concept equipped with a stereo camera and an external illumination source. Finally, we demonstrate the efficacy of our proposed approach in both a Lunar simulation environment and on data collected during a field test at Cinder Lakes, Arizona.
- 2 October 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Field Robotics
- Vol. 1, 213-230
ShadowNav: Autonomous Global Localization for Lunar Navigation in Darkness
The ability to determine the position of a rover in an inertial frame autonomously is a crucial capability necessary for the next generation of surface rover missions on other planetary bodies. Currently, most on-going rover missions utilize ground-in-the-loop interventions to manually correct for drift in the position estimate and this human supervision bottlenecks the distance over which rovers can operate autonomously and carry out scientific measurements. In this paper, we present ShadowNav, an autonomous approach for global 2D localization on the Moon with an emphasis on driving in darkness and at nighttime. Our approach uses the leading edge of Lunar craters as landmarks and a particle filtering approach to associate detected craters with known ones on an offboard map. We discuss the key design decisions in developing the ShadowNav framework for use with a Lunar rover concept equipped with a stereo camera and an external illumination source. Finally, we demonstrate the efficacy of our proposed approach in both a Lunar simulation environment and on data collected during a field test at Cinder Lakes, Arizona.
- Open Access
- 1 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Field Robotics
- Vol. 2, 1432-1506
NeBula: TEAM CoSTAR's Robotic Autonomy Solution that Won Phase II of DARPA Subterranean Challenge
- 1 July 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Field Robotics
- Vol. 2, 1432-1506
Open AccessNeBula: TEAM CoSTAR's Robotic Autonomy Solution that Won Phase II of DARPA Subterranean Challenge
- 27 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 29 (3) , 24-33
Testing Gecko-Inspired Adhesives With Astrobee Aboard the International Space Station: Readying the Technology for Space
Gecko-inspired adhesives can allow free-flying space robots to grasp and manipulate large items or anchor themselves on smooth surfaces. In this article, we report on the first tests conducted using gecko-inspired adhesives on a gripper attached to an Astrobee free-flying robot operating inside the International Space Station (ISS). We present results from on-ground testing as well as two on-orbit sessions conducted during early 2021. Recorded data demonstrated that an adhesive gripper for Astrobee could provide 3.15 N of force for manual perching. The adhesives functioned as anticipated, despite a lengthy storage period. The results also highlighted some considerations for future adhesive gripping in space with free-flying robots. We discuss these topics along with system design considerations for successful implementation aboard the ISS, raising the readiness of this technology for a space-grade environment.
- 27 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics & Automation Magazine
- Vol. 29 (3) , 24-33
Testing Gecko-Inspired Adhesives With Astrobee Aboard the International Space Station: Readying the Technology for Space
Gecko-inspired adhesives can allow free-flying space robots to grasp and manipulate large items or anchor themselves on smooth surfaces. In this article, we report on the first tests conducted using gecko-inspired adhesives on a gripper attached to an Astrobee free-flying robot operating inside the International Space Station (ISS). We present results from on-ground testing as well as two on-orbit sessions conducted during early 2021. Recorded data demonstrated that an adhesive gripper for Astrobee could provide 3.15 N of force for manual perching. The adhesives functioned as anticipated, despite a lengthy storage period. The results also highlighted some considerations for future adhesive gripping in space with free-flying robots. We discuss these topics along with system design considerations for successful implementation aboard the ISS, raising the readiness of this technology for a space-grade environment.
- Open Access
Learning Mixed-Integer Convex Optimization Strategies for Robot Planning and Control
Mixed-integer convex programming (MICP) has seen significant algorithmic and hardware improvements with several orders of magnitude solve time speedups compared to 25 years ago. Despite these advances, MICP has been rarely applied to real-world robotic control because the solution times are still too slow for online applications. In this work, we present the CoCo (Combinatorial Offline, Convex Online) framework to solve MICPs arising in robotics at very high speed. CoCo encodes the combinatorial part of the optimal solution into a strategy. Using data collected from offline problem solutions, we train a multiclass classifier to predict the optimal strategy given problem-specific parameters such as states or obstacles. Compared to previous approaches, we use task-specific strategies and prune redundant ones to significantly reduce the number of classes the predictor has to select from, thereby greatly improving scalability. Given the predicted strategy, the control task becomes a small convex optimization problem that we can solve in milliseconds. Numerical experiments on a cart-pole system with walls, a free-flying space robot, and task-oriented grasps show that our method provides not only 1 to 2 orders of magnitude speedups compared to state-of-the-art solvers but also performance close to the globally optimal MICP solution.
Open AccessLearning Mixed-Integer Convex Optimization Strategies for Robot Planning and Control
Mixed-integer convex programming (MICP) has seen significant algorithmic and hardware improvements with several orders of magnitude solve time speedups compared to 25 years ago. Despite these advances, MICP has been rarely applied to real-world robotic control because the solution times are still too slow for online applications. In this work, we present the CoCo (Combinatorial Offline, Convex Online) framework to solve MICPs arising in robotics at very high speed. CoCo encodes the combinatorial part of the optimal solution into a strategy. Using data collected from offline problem solutions, we train a multiclass classifier to predict the optimal strategy given problem-specific parameters such as states or obstacles. Compared to previous approaches, we use task-specific strategies and prune redundant ones to significantly reduce the number of classes the predictor has to select from, thereby greatly improving scalability. Given the predicted strategy, the control task becomes a small convex optimization problem that we can solve in milliseconds. Numerical experiments on a cart-pole system with walls, a free-flying space robot, and task-oriented grasps show that our method provides not only 1 to 2 orders of magnitude speedups compared to state-of-the-art solvers but also performance close to the globally optimal MICP solution.
- 16 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 1447-1454
CoCo: Online Mixed-Integer Control Via Supervised Learning
Many robotics problems, from robot motion planning to object manipulation, can be modeled as mixed-integer convex program (MICPs). However, state-of-the-art algorithms are still unable to solve MICPs for control problems quickly enough for online use and existing heuristics can typically only find suboptimal solutions that might degrade robot performance. In this work, we turn to data-driven methods and present the Combinatorial Offline, Convex Online (CoCo) algorithm for quickly finding high quality solutions for MICPs. CoCo consists of a two-stage approach. In the offline phase, we train a neural network classifier that maps the problem parameters to a logical strategy , which we define as the discrete arguments and relaxed big-M constraints associated with the optimal solution for that problem. Online, the classifier is applied to select a candidate logical strategy given new problem parameters; applying this logical strategy allows us to solve the original MICP as a convex optimization problem. We show through numerical experiments how CoCo finds near optimal solutions to MICPs arising in robot planning and control with 1 to 2 orders of magnitude solution speedup compared to other data-driven approaches and solvers.
- 16 December 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 7 (2) , 1447-1454
CoCo: Online Mixed-Integer Control Via Supervised Learning
Many robotics problems, from robot motion planning to object manipulation, can be modeled as mixed-integer convex program (MICPs). However, state-of-the-art algorithms are still unable to solve MICPs for control problems quickly enough for online use and existing heuristics can typically only find suboptimal solutions that might degrade robot performance. In this work, we turn to data-driven methods and present the Combinatorial Offline, Convex Online (CoCo) algorithm for quickly finding high quality solutions for MICPs. CoCo consists of a two-stage approach. In the offline phase, we train a neural network classifier that maps the problem parameters to a logical strategy , which we define as the discrete arguments and relaxed big-M constraints associated with the optimal solution for that problem. Online, the classifier is applied to select a candidate logical strategy given new problem parameters; applying this logical strategy allows us to solve the original MICP as a convex optimization problem. We show through numerical experiments how CoCo finds near optimal solutions to MICPs arising in robot planning and control with 1 to 2 orders of magnitude solution speedup compared to other data-driven approaches and solvers.